@conference{LIPAR_NeurIPS,

title = {Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery},

author = {Dennis Menn and Yuedong Yang and Bokun Wang and Xiwen Wei and Mustafa Munir and Feng Liang and Radu Marculescu and Chenfeng Xu and Diana Marculescu},

year  = {2026},

date = {2026-12-07},

booktitle = {Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2026)},

keywords = {},

pubstate = {forthcoming},

tppubtype = {conference}

}

@conference{AttentionViG,

title = {AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs},

author = {Hakan Emre Gedik and Andrew Martin and Mustafa Munir and Oguzhan Baser and Radu Marculescu and Sandeep P. Chinchali and Alan C. Bovik},

url = {https://www.arxiv.org/abs/2509.25570},

year  = {2026},

date = {2026-09-26},

urldate = {2025-09-29},

booktitle = {The Fifth Learning on Graphs Conference},

keywords = {Deep Learning, Deep Learning Architecture, Efficient AI, Graph Neural Network},

pubstate = {forthcoming},

tppubtype = {conference}

}

@conference{FuelGauge_CVPR_26,

title = {Fuel Gauge: Estimating Chain-of-Thought Length Ahead of Time in Large Multimodal Models},

author = {Yuedong Yang and Xiwen Wei and Mustafa Munir and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/CVPR2026/papers/Yang_Fuel_Gauge_Estimating_Chain-of-Thought_Length_Ahead_of_Time_in_Large_CVPR_2026_paper.pdf},

year  = {2026},

date = {2026-06-15},

urldate = {2026-06-15},

booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ObjectAlign_CVPRW,

title = {ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction},

author = {Mustafa Munir and Harsh Goel and Xiwen Wei and Minkyu Choi and Sahil Shah and Kartikeya Bhardwaj and Paul Whatmough and Sandeep Chinchali and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/CVPR2026W/EDGE/html/Munir_ObjectAlign_Neuro-Symbolic_Object_Consistency_Verification_and_Correction_CVPRW_2026_paper.html},

year  = {2026},

date = {2026-06-08},

urldate = {2026-06-08},

booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{SAFLe_2026,

title = {Single-Round Scalable Analytic Federated Learning},

author = {Alan Bacellar and Mustafa Munir and Felipe M. G. Fran\c{c}a and Priscila M. V. Lima and Radu Marculescu and Lizy K. John},

url = {https://openaccess.thecvf.com/content/CVPR2026/papers/Bacellar_Single-Round_Scalable_Analytic_Federated_Learning_CVPR_2026_paper.pdf},

year  = {2026},

date = {2026-06-01},

booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},

keywords = {Federated Learning},

pubstate = {published},

tppubtype = {conference}

}

@conference{SmoothDiffusion_WACV_2026,

title = {SmoothDiffusion-VE: Real-time Generative Video Editing Using Adaptive Feature Cache},

author = {Mustafa Munir and Sophia Zalewski and Shiqiu Liu and David Tarjan and Sushmitha Belede and Anjul Patney and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/WACV2026/html/Munir_SmoothDiffusion-VE_Real-time_Generative_Video_Editing_Using_Adaptive_Feature_Cache_WACV_2026_paper.html},

year  = {2026},

date = {2026-03-02},

urldate = {2026-03-02},

booktitle = {2026 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2026)},

keywords = {Edge AI, Efficient AI, Efficient Inference, Generative AI},

pubstate = {published},

tppubtype = {conference}

}

@conference{AdaptViG_WACV_2026,

title = {AdaptViG: Adaptive Vision GNN with Exponential Decay Gating},

author = {Mustafa Munir and Md Mostafijur Rahman and Radu Marculescu},

url = {https://ieeexplore.ieee.org/abstract/document/11492666},

year  = {2026},

date = {2026-03-02},

urldate = {2026-03-02},

booktitle = {2026 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2026)},

keywords = {Deep Learning, Deep Learning Architecture, Efficient AI, Featured, Graph Neural Network},

pubstate = {published},

tppubtype = {conference}

}

@conference{NeuS-QA,

title = {NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic Reasoning},

author = {Sahil Shah and S P Sharan and Harsh Goel and Minkyu Choi and Mustafa Munir and Manvik Pasula and Radu Marculescu and Sandeep Chinchali},

url = {https://ojs.aaai.org/index.php/AAAI/article/view/37834},

year  = {2026},

date = {2026-01-15},

urldate = {2026-01-15},

booktitle = {AAAI Conference on Artificial Intelligence 2026},

volume = {40},

number = {11},

pages = {8805\textendash8813},

keywords = {Deep Learning, Efficient AI, Featured, Generative AI},

pubstate = {published},

tppubtype = {conference}

}

@conference{SearchViG_LOG_2025,

title = {SearchViG: Optimal Vision GNNs via Ramanujan Spectral Optimization},

author = {Mustafa Munir and Md Mostafijur Rahman and Xiwen Wei and Yuedong Yang and Radu Marculescu},

url = {https://openreview.net/pdf?id=cmEzgaYIJC},

year  = {2025},

date = {2025-12-15},

urldate = {2025-12-15},

booktitle = {The Fourth Learning on Graphs Conference (LOG 2025)},

keywords = {Deep Learning, Deep Learning Architecture, Dynamic networks, Efficient AI, Featured, Graph Neural Network},

pubstate = {published},

tppubtype = {conference}

}

@conference{lomix@rahman,

title = {LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation},

author = {Md Mostafijur Rahman and Radu Marculescu},

url = {https://papers.nips.cc/paper_files/paper/2025/file/5f0e54e34ba4c30fbc6f229986dbffb4-Paper-Conference.pdf},

year  = {2025},

date = {2025-12-03},

urldate = {2025-12-03},

publisher = {Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2025)},

keywords = {Deep Learning, Logit Mixing, Medical Image Segmentation, Medical Imaging, Supervision},

pubstate = {published},

tppubtype = {conference}

}

@conference{MODE_2025,

title = {Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models},

author = {Xiwen Wei and Mustafa Munir and Radu Marculescu},

url = {https://openreview.net/pdf?id=CBsANtjBV4},

year  = {2025},

date = {2025-12-03},

urldate = {2025-12-03},

booktitle = {Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2025)},

keywords = {Continual Learning, Deep Learning, Generative AI},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Batteryless Gesture Recognition Via Learned Sampling},

author = {Geffen Cooper and Radu Marculescu},

url = {https://ieeexplore.ieee.org/abstract/document/11337480},

year  = {2025},

date = {2025-11-03},

urldate = {2025-11-03},

publisher = {IEEE International Conference on Body Sensor Networks},

keywords = {batteryless sensors, energy harvesting, Internet of Things},

pubstate = {published},

tppubtype = {conference}

}

@conference{mkunet@rahman,

title = {MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation},

author = {Md Mostafijur Rahman and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/ICCV2025W/CVAMD/html/Rahman_MK-UNet_Multi-kernel_Lightweight_CNN_for_Medical_Image_Segmentation_ICCVW_2025_paper.html},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {Proceedings of the International Conference on Computer Vision (ICCV) Workshops},

abstract = {In this paper, we introduce MK-UNet, a paradigm shift towards ultra-lightweight, multi-kernel U-shaped CNNs tailored for medical image segmentation. Central to MK-UNet is the multi-kernel depth-wise convolution block (MKDC) we design to adeptly process images through multiple kernels, while capturing complex multi-resolution spatial relationships. MK-UNet also emphasizes the images salient features through sophisticated attention mechanisms, including channel, spatial, and grouped gated attention. Our MK-UNet network, with a modest computational footprint of only 0.316 M parameters and 0.314 G FLOPs, represents not only a remarkably lightweight, but also significantly improved segmentation solution that provides higher accuracy over state-of-the-art (SOTA) methods across six binary medical imaging benchmarks. Specifically, MK-UNet outperforms TransUNet in DICE score with nearly 333x and 123x fewer parameters and FLOPs, respectively. Similarly, when compared against UNeXt, MK-UNet exhibits superior segmentation performance, improving the DICE score up to 6.7% margins while operating with 4.7 x fewer# Params. Our MK-UNet also outperforms other recent lightweight networks, such as MedT, CMUNeXt, EGE-UNet, and Rolling-UNet, with much lower computational resources. This leap in performance, coupled with drastic computational gains, positions MK-UNet as an unparalleled solution for real-time, high-fidelity medical diagnostics in resource-limited settings, such as point-of-care devices. Our implementation is available at https://github. com/SLDGroup/MK-UNet.},

keywords = {Efficient AI, Lightweight Architecture, Medical Image Segmentation, Multi-kernel Convolutions},

pubstate = {published},

tppubtype = {conference}

}

@conference{VCMamba_ICCV_2025,

title = {VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation},

author = {Mustafa Munir and Alex Zhang and Radu Marculescu},

url = {https://arxiv.org/abs/2509.04669},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {Proceedings of the International Conference on Computer Vision (ICCV 2025) Workshops},

abstract = {Recent advances in Vision Transformers (ViTs) and State Space Models (SSMs) have challenged the dominance of Convolutional Neural Networks (CNNs) in computer vision. ViTs excel at capturing global context, and SSMs like Mamba offer linear complexity for long sequences, yet they do not capture fine-grained local features as effectively as CNNs. Conversely, CNNs possess strong inductive biases for local features but lack the global reasoning capabilities of transformers and Mamba. To bridge this gap, we introduce VCMamba, a novel vision backbone that integrates the strengths of CNNs and multi-directional Mamba SSMs. VCMamba employs a convolutional stem and a hierarchical structure with convolutional blocks in its early stages to extract rich local features. These convolutional blocks are then processed by later stages incorporating multi-directional Mamba blocks designed to efficiently model long-range dependencies and global context. This hybrid design allows for superior feature representation while maintaining linear complexity with respect to image resolution. We demonstrate VCMamba’s effectiveness through extensive experiments on ImageNet-1K classification and ADE20K semantic segmentation. Our VCMamba-B achieves 82.6% top-1 accuracy on ImageNet-1K, surpassing PlainMamba-L3 by 0.3% with 37% fewer parameters, and outperforming Vision GNN-B by 0.3% with 64% fewer parameters. Furthermore, VCMamba-B obtains 47.1 mIoU on ADE20K, exceeding EfficientFormer-L7 by 2.0 mIoU while utilizing 62% fewer parameters. Code is available at https://github.com/Wertyuui345/VCMamba.},

keywords = {Deep Learning Architecture, Efficient AI, Featured, Lightweight Architecture, Model Compression \& Optimization},

pubstate = {published},

tppubtype = {conference}

}

@conference{efficientmednext@rahman,

title = {EfficientMedNeXt: Multi-Receptive Dilated Convolutions for Medical Image Segmentation},

author = {Md Mostafijur Rahman and Mustafa Munir and Radu Marculescu},

url = {https://link.springer.com/chapter/10.1007/978-3-032-04965-0_19},

year  = {2025},

date = {2025-09-23},

urldate = {2025-09-23},

publisher = {International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)},

abstract = {In this work, we introduce EfficientMedNeXt\textemdasha lightweight, high-performance segmentation architecture developed through a two-phase optimization process applied to the MedNeXt architecture. To this end, we first optimize the decoder by reducing the high-resolution redundancy and unifying the decoder channels across stages for enhanced efficiency. Then, we introduce a new Dilated Multi-Receptive Field Block (DMRFB) to capture the multi-scale spatial context efficiently without increasing the kernel sizes and relying on the channel expansion convolutions. Extensive evaluations on BTCV, FeTA, and MSD show that EfficientMedNeXt-L achieves 87.0% DICE score on BTCV (+1.04% over MedNeXt-L) with 96.5% fewer parameters and 77.03% lower FLOPs. In addition, EfficientMedNeXt-S offers comparable DICE score, improved HD95, and 78.1% higher throughput while reducing parameters by 98.5% and FLOPs by 95%. These results demonstrate EfficientMedNeXt’s efficiency and accuracy, making it well-suited for real-world clinical applications. Code will be released upon acceptance.},

keywords = {3D Segmentation, Deep Learning Architecture, Efficient AI, Efficient Inference, Featured, Medical Image Segmentation},

pubstate = {published},

tppubtype = {conference}

}

@conference{prime@rahman,

title = {Training-Free Dataset Pruning for Polyp Segmentation via Community Detection in Similarity Networks},

author = {Md Mostafijur Rahman and Radu Marculescu},

url = {https://openreview.net/pdf?id=VQX4B2A2Y0},

year  = {2025},

date = {2025-07-09},

urldate = {2025-07-09},

publisher = {Medical Imaging with Deep Learning (MIDL) },

abstract = {Recent advances in deep learning have been driven by the availability of larger datasets and more complex models; however, this progress comes at the expense of substantial computational and annotation costs. To address these issues, we introduce a novel, training-free dataset pruning method,PRIME, targeting polyp segmentation in medical imaging. To this end, PRIME constructs a similarity network among the images in the target dataset and then applies community detection to retain a much smaller, yet representative subset of images from the original dataset. Unlike existing methods that require model training for dataset pruning, our PRIME completely avoids model training, thus significantly reducing computational demands. The reduction in the training dataset cuts 56.2% data annotation costs and enables 2.3× faster training of polyp segmentation models, with only a 0.5% drop in the DICE score. Consequently, our PRIME enables efficient training, fine-tuning, and domain adaptation across medical centers, thus offering a cost-effective solution for deep learning in polyp segmentation.},

keywords = {Community Detection, Dataset Pruning, Featured, Medical Image Segmentation, Polyp segmentation, Training-free},

pubstate = {published},

tppubtype = {conference}

}

@conference{Data_to_Design_Frequency,

title = {From Data to Design: Leveraging Frequency Statistics for Efficient Neural Network Architectures},

author = {Mustafa Munir and Guihong Li and Md Mostafijur Rahman and Alex Zhang and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/CVPR2025W/eLVM/html/Munir_From_Data_to_Design_Leveraging_Frequency_Statistics_for_Efficient_Neural_CVPRW_2025_paper.html},

year  = {2025},

date = {2025-06-11},

urldate = {2025-06-11},

booktitle = {2025 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},

keywords = {Deep Learning Architecture, Efficient Inference, Model Compression \& Optimization, Neural Architecture Search},

pubstate = {published},

tppubtype = {conference}

}

@conference{effidec3d@rahman,

title = {EffiDec3D: An Optimized Decoder for High-Performance and Efficient 3D Medical Image Segmentation},

author = {Md Mostafijur Rahman and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/CVPR2025/html/Rahman_EffiDec3D_An_Optimized_Decoder_for_High-Performance_and_Efficient_3D_Medical_CVPR_2025_paper.html},

year  = {2025},

date = {2025-06-10},

urldate = {2025-06-10},

publisher = {Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)},

abstract = {Recent 3D deep networks such as SwinUNETR, SwinUNETRv2, and 3D UX-Net have shown promising performance by leveraging self-attention and large-kernel convolutions to capture the volumetric context. However, their substantial computational requirements limit their use in real-time and resource-constrained environments. The high #FLOPs and #Params in these networks stem largely from complex decoder designs with high-resolution layers and

excessive channel counts. In this paper, we propose EffiDec3D, an optimized 3D decoder that employs a channel reduction strategy across all decoder stages, which sets the number of channels to the minimum needed for accurate feature representation. Additionally, EffiDec3D removes the high-resolution layers when their contribution

to segmentation quality is minimal. Our optimized EffiDec3D decoder achieves a 96.4% reduction in #Params and a 93.0% reduction in #FLOPs compared to the decoder of original 3D UX-Net. Similarly, for SwinUNETR and SwinUNETRv2 (which share an identical decoder), we observe reductions of 94.9% in #Params and 86.2% in #FLOPs. Our extensive experiments on 12 different medical imaging tasks confirm that EffiDec3D not only significantly reduces the computational demands, but also maintains a performance level comparable to original models, thus establishing a new standard for efficient 3D medical image segmentation. Our implementation is available at https://github.com/SLDGroup/EffiDec3D.},

keywords = {3D Segmentation, Deep Learning Architecture, Efficient AI, Efficient Decoder, Featured, Medical Image Segmentation},

pubstate = {published},

tppubtype = {conference}

}

@conference{loca,

title = {Federated Continual Learning for Monocular Depth Estimation in Dynamic Indoor Environments},

author = {Allen-Jasmin Farcas and Hyun Joon Song and Radu Marculescu},

url = {https://ieeexplore.ieee.org/document/11096257},

year  = {2025},

date = {2025-06-09},

urldate = {2025-06-09},

booktitle = {21st International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT 2025)},

keywords = {Continual Learning, Federated Learning, Monocular Depth Estimation},

pubstate = {published},

tppubtype = {conference}

}

@conference{liti,

title = {Demo Abstract: Lightweight Training and Inference for Self-Supervised Depth Estimation on Edge Devices},

author = {Allen-Jasmin Farcas and Radu Marculescu},

url = {https://dl.acm.org/doi/10.1145/3715014.3724373},

year  = {2025},

date = {2025-05-07},

urldate = {2025-05-07},

booktitle = {Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems (SenSys 2025)},

keywords = {Edge AI, Efficient Inference, Federated Learning, Monocular Depth Estimation, Self-Supervised Learning},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Health Status Discovery for Online Bidirectional Contact Tracing and Disease Aware Navigation},

author = {Sofia Hurtado and Radu Marculescu},

doi = {10.1109/CAI64502.2025.00084},

year  = {2025},

date = {2025-05-06},

booktitle = {2025 IEEE Conference on Artificial Intelligence (CAI)},

pages = {457-462},

keywords = {Disease Mitigation, Multi Agent Reinforcement Learning, Networks},

pubstate = {published},

tppubtype = {conference}

}

@conference{ONLINE_LORA_WACV_2025,

title = {Online-LoRA: Task-Free Online Continual Learning via Low Rank Adaptation},

author = {Xiwen Wei and Guihong Li and Radu Marculescu},

url = {https://ieeexplore.ieee.org/document/10943985},

year  = {2025},

date = {2025-03-06},

urldate = {2025-01-06},

booktitle = {2025 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)},

abstract = {Catastrophic forgetting is a significant challenge in online continual learning (OCL), especially for non-stationary data streams that do not have well-defined task boundaries. This challenge is exacerbated by the memory constraints and privacy concerns inherent in rehearsal buffers. To tackle catastrophic forgetting, in this paper, we introduce Online-LoRA, a novel framework for task-free OCL. Online-LoRA allows to finetune pre-trained Vision Transformer (ViT) models in real-time to address the limitations of rehearsal buffers and leverage pre-trained models' performance benefits. As the main contribution, our approach features a novel online weight regularization strategy to identify and consolidate important model parameters. Moreover, Online-LoRA leverages the training dynamics of loss values to enable the automatic recognition of the data distribution shifts. Extensive experiments across many task-free OCL scenarios and benchmark datasets (including CIFAR-100, ImageNet-R, ImageNet-S, CUB-200 and CORe50) demonstrate that Online-LoRA can be robustly adapted to various ViT architectures, while achieving better performance compared to SOTA methods.},

keywords = {Vision Transformer},

pubstate = {published},

tppubtype = {conference}

}

@conference{RapidNet_WACV_2025,

title = {RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone},

author = {Mustafa Munir and Md Mostafijur Rahman and Radu Marculescu},

url = {https://ieeexplore.ieee.org/document/10943953},

year  = {2025},

date = {2025-03-03},

urldate = {2025-03-03},

booktitle = {2025 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)},

journal = {2025 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)},

keywords = {Deep Learning Architecture, Edge AI, Efficient Inference, Featured, Model Compression \& Optimization},

pubstate = {published},

tppubtype = {conference}

}

@conference{ADA_VE_WACV_2025,

title = {Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior},

author = {Tanvir Mahmud and Mustafa Munir and Radu Marculescu and Diana Marculescu},

url = {https://ieeexplore.ieee.org/document/10943436},

year  = {2025},

date = {2025-02-28},

urldate = {2025-02-28},

booktitle = {2025 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)},

keywords = {Efficient Inference, Generative AI},

pubstate = {published},

tppubtype = {conference}

}

@conference{LogViG_LOG_2024,

title = {Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs},

author = {Mustafa Munir and Alex Zhang and Radu Marculescu},

url = {https://github.com/mmunir127/LogViG-Official},

year  = {2024},

date = {2024-11-26},

urldate = {2024-11-26},

booktitle = {The Third Learning on Graphs Conference (LOG 2024)},

keywords = {Deep Learning Architecture, Edge AI, Graph Neural Network},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Packet Pruning: Finding Better Energy Spending Policies for Batteryless Human Activity Recognition},

author = {Geffen Cooper and Radu Marculescu},

url = {https://ieeexplore.ieee.org/document/10780463},

year  = {2024},

date = {2024-10-16},

urldate = {2024-10-16},

publisher = {IEEE International Conference on Body Sensor Networks (BSN 2024)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{GreedyViG_CVPR_2024,

title = {GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs},

author = {Mustafa Munir and William Avery and Md Mostafijur Rahman and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/CVPR2024/papers/Munir_GreedyViG_Dynamic_Axial_Graph_Construction_for_Efficient_Vision_GNNs_CVPR_2024_paper.pdf},

year  = {2024},

date = {2024-06-19},

urldate = {2024-06-19},

booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

abstract = {Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. To solve this issue, we propose a new method for designing ViGs, Dynamic Axial Graph Construction (DAGC), which is more efficient than KNN as it limits the number of considered graph connections made within an image. Additionally, we propose a novel CNN-GNN architecture, GreedyViG, which uses DAGC. Extensive experiments show that GreedyViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification, object detection, instance segmentation, and semantic segmentation tasks. Our smallest model, GreedyViG-S, achieves 81.1% top-1 accuracy on ImageNet-1K, 2.9% higher than Vision GNN and 2.2% higher than Vision HyperGraph Neural Network (ViHGNN), with less GMACs and a similar number of parameters. Our largest model, GreedyViG-B obtains 83.9% top-1 accuracy, 0.2% higher than Vision GNN, with a 66.6% decrease in parameters and a 69% decrease in GMACs. GreedyViG-B also obtains the same accuracy as ViHGNN with a 67.3% decrease in parameters and a 71.3% decrease in GMACs. Our work shows that hybrid CNNGNN architectures not only provide a new avenue for designing efficient models, but that they can also exceed the performance of current state-of-the-art models.},

keywords = {Deep Learning Architecture, Dynamic networks, Edge AI, Efficient Inference, Graph Neural Network},

pubstate = {published},

tppubtype = {conference}

}

@conference{EMCAD_CVPR_2024,

title = {EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation},

author = {Md Mostafijur Rahman and Mustafa Munir and Radu Marculescu },

url = {https://openaccess.thecvf.com/content/CVPR2024/papers/Rahman_EMCAD_Efficient_Multi-scale_Convolutional_Attention_Decoding_for_Medical_Image_Segmentation_CVPR_2024_paper.pdf},

year  = {2024},

date = {2024-06-17},

urldate = {2024-06-17},

publisher = {Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)},

abstract = {An efficient and effective decoding mechanism is crucial in medical image segmentation, especially in scenarios with limited computational resources. However, these decoding mechanisms usually come with high computational costs. To address this concern, we introduce EMCAD, a new efficient multi-scale convolutional attention decoder, designed to optimize both performance and computational efficiency. EMCAD leverages a unique multi-scale depth-wise convolution block, significantly enhancing feature maps through multi-scale convolutions. EMCAD also employs channel, spatial, and grouped (large-kernel) gated attention mechanisms, which are highly effective at capturing intricate spatial relationships while focusing on salient regions. By employing group and depth-wise convolution, EMCAD is very efficient and scales well (e.g., only 1.91M parameters and 0.381G FLOPs are needed when using a standard encoder). Our rigorous evaluations across 12 datasets that belong to six medical image segmentation tasks reveal that EMCAD achieves state-of-the-art (SOTA) performance with 79.4% and 80.3% reduction in #Params and #FLOPs, respectively. Moreover, EMCAD’s adaptability to different encoders and versatility across segmentation tasks further establish EMCAD as a promising tool, advancing the field towards more efficient and accurate medical image analysis. Our implementation is available at https://github.com/SLDGroup/EMCAD.},

keywords = {Deep Learning Architecture, Efficient Decoder, Medical Image Segmentation, Multi-scale Depth-wise Convolutions, Vision Transformer},

pubstate = {published},

tppubtype = {conference}

}

@conference{ppsam@rahman,

title = {PP-SAM: Perturbed Prompts for Robust Adaption of Segment Anything Model for Polyp Segmentation},

author = {Md Mostafijur Rahman and Mustafa Munir and Debesh Jha and Ulas Bagci and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/CVPR2024W/DEF-AI-MIA/papers/Rahman_PP-SAM_Perturbed_Prompts_for_Robust_Adaption_of_Segment_Anything_Model_CVPRW_2024_paper.pdf},

year  = {2024},

date = {2024-06-17},

urldate = {2024-06-17},

booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},

abstract = {The Segment Anything Model (SAM), originally designed for general-purpose segmentation tasks, has been used recently for polyp segmentation. Nonetheless, finetuning SAM with data from new imaging centers or clinics poses significant challenges. This is because this necessitates the creation of an expensive and time-intensive annotated dataset, along with the potential for variability in user prompts during inference. To address these issues, we propose a robust fine-tuning technique, PP-SAM, that allows SAM to adapt to the polyp segmentation task with limited images. To this end, we utilize variable perturbed bounding box prompts (BBP) to enrich the learning context and enhance the model’s robustness to BBP perturbations during inference. Rigorous experiments on polyp segmentation benchmarks reveal that our variable BBP perturbation significantly improves model resilience. Notably, on Kvasir, 1-shot fine-tuning boosts the DICE score by 20% and 37% with 50 and 100-pixel BBP perturbations during inference, respectively. Moreover, our experiments show that 1-shot, 5-shot, and 10-shot PP-SAM with 50-pixel perturbations during inference outperform a recent state-ofthe-art (SOTA) polyp segmentation method by 26%, 7%, and 5% DICE scores, respectively. Our results motivate the broader applicability of our PP-SAM for other medical imaging tasks with limited samples. Our implementation is available at https://github.com/SLDGroup/PP-SAM.},

keywords = {Limited data, Perturbed prompts, Polyp segmentation, Robustness, SAM},

pubstate = {published},

tppubtype = {conference}

}

@conference{MobileViGv2,

title = {Scaling Graph Convolutions for Mobile Vision},

author = {William Avery and Mustafa Munir and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/CVPR2024W/MAI/papers/Avery_Scaling_Graph_Convolutions_for_Mobile_Vision_CVPRW_2024_paper.pdf},

year  = {2024},

date = {2024-06-17},

urldate = {2024-06-17},

booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},

keywords = {Deep Learning Architecture, Edge AI, Embedded Systems, Internet of Things},

pubstate = {published},

tppubtype = {conference}

}

@conference{chessfl,

title = {CHESSFL: Clustering Hierarchical Embeddings for Semi-Supervised Federated Learning},

author = {Allen-Jasmin Farcas and Myungjin Lee and Ali Payani and Ramana Rao Kompella and Hugo Latapie and Radu Marculescu},

url = {https://ieeexplore.ieee.org/document/10562180},

year  = {2024},

date = {2024-05-13},

urldate = {2024-05-13},

booktitle = {Proceedings of the 9th ACM/IEEE Conference on Internet of Things Design and Implementation},

keywords = {Federated Learning, Hierarchical Federated Learning, Semi-supervised learning},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Beyond Thresholds: A General Approach to Sensor Selection for Practical Deep Learning-based HAR},

author = {Geffen Cooper and Radu Marculescu},

url = {https://ieeexplore.ieee.org/abstract/document/10562185},

year  = {2024},

date = {2024-05-13},

urldate = {2024-05-13},

booktitle = {Proceedings of the 9th ACM/IEEE Conference on Internet of Things Design and Implementation},

keywords = {Cascaded Inference, Efficient Inference, Human Activity Recognition, Sensor Selection},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Demo Abstract: Online Training and Inference for On-Device Monocular Depth Estimation},

author = {Allen-Jasmin Farcas and Geffen Cooper and Hyun Joon Song and Afnan Mir and Vincent Liew and Chloe Tang and Prithvi Senthilkumar and Tiani Chen-Troester and Radu Marculescu},

url = {https://ieeexplore.ieee.org/abstract/document/10562188},

year  = {2024},

date = {2024-05-13},

booktitle = {Proceedings of the 9th ACM/IEEE Conference on Internet of Things Design and Implementation},

keywords = {Edge AI, Efficient Inference, Monocular Depth Estimation, On-device Training},

pubstate = {published},

tppubtype = {conference}

}

@conference{WACV2024Mostafij,

title = {G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation},

author = {Md Mostafijur Rahman and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/WACV2024/html/Rahman_G-CASCADE_Efficient_Cascaded_Graph_Convolutional_Decoding_for_2D_Medical_Image_WACV_2024_paper.html},

year  = {2024},

date = {2024-01-04},

urldate = {2024-01-04},

booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},

pages = {7728-7737},

keywords = {Deep Learning Architecture, Graph Neural Network, Medical Image Segmentation},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Efficient Low-rank Backpropagation for Vision Transformer Adaptation},

author = {Yuedong Yang and Hung-Yueh Chiang and Guihong Li and Diana Marculescu and Radu Marculescu},

url = {https://radum.ece.utexas.edu/wp-content/uploads/2023/09/LBP_WHT.pdf},

year  = {2023},

date = {2023-12-11},

urldate = {2023-12-11},

publisher = {Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS) 2023},

abstract = {The increasing scale of vision transformers (ViT) has made the efficient fine-tuning of these large models for specific needs a significant challenge in various applications. This issue originates from the computationally demanding matrix multiplications required during the backpropagation process through linear layers in ViT. In this paper, we tackle this problem by proposing a new Low-rank BackPropagation via Walsh-Hadamard Transformation (LBP-WHT) method. Intuitively, LBP-WHT projects the gradient into a low-rank space and carries out backpropagation. This approach substantially reduces the computation needed for adapting ViT, as matrix multiplication in the low-rank space is far less resource-intensive. We conduct extensive experiments with different models (ViT, hybrid convolution-ViT model) on multiple datasets to demonstrate the effectiveness of our method. For instance, when adapting an EfficientFormer-L1 model on CIFAR100, our LBP-WHT achieves 10.4% higher accuracy than the state-of-the-art baseline, while requiring 9 MFLOPs less computation. As the first work to accelerate ViT adaptation with low-rank backpropagation, our LBP-WHT method is complementary to many prior efforts and can be combined with them for better performance.},

keywords = {On-device Training, Vision Transformer},

pubstate = {published},

tppubtype = {conference}

}

@conference{Hurtado2023Q,

title = {Quarantine in Motion: A Graph Learning and Multi-Agent Reinforcement Learning Framework to Reduce Disease Transmission Without Lockdown},

author = {Sofia Hurtado and Radu Marculescu},

url = {https://ieeexplore.ieee.org/document/10068686},

year  = {2023},

date = {2023-11-06},

urldate = {2023-11-06},

booktitle = {Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2023)},

abstract = {Exposure notification applications are designed to help trace disease spreading by alerting exposed individuals to get tested. However, false alarms can cause users to become hesitant to respond, making the applications ineffective. To address the shortcomings of slow manual contact tracing, costly lockdowns, and unreliable exposure notification applications, better disease mitigation strategies are needed. In this study, we propose a new disease mitigation paradigm where people can reduce infection spreading while maintaining some mobility (i.e., Quarantine in Motion). Our approach utilizes Graph Neural Networks (GNNs) to predict disease hotspots such as restaurants, shops and parks, and Multi-Agent Reinforcement Learning (MARL) to collaboratively manage human mobility to reduce disease transmission. As proof of concept, we simulate an infection using real-world mobility data from New York City (over 200,000 devices) and Austin (over 36,000 devices) and train 10,000 agents from each city to manage disease dynamics. Through simulation, we show that a trained population suppresses their reproduction rate below 1, thereby mitigating the outbreak.},

keywords = {Epidemics, GPS, Graph Neural Network, Multi Agent Reinforcement Learning},

pubstate = {published},

tppubtype = {conference}

}

@conference{tips_icml2023,

title = {TIPS: Topologically Important Path Sampling for Anytime Neural Networks},

author = {Li, Guihong and Bhardwaj, Kartikeya and Yang, Yuedong and Marculescu, Radu},

url = {https://arxiv.org/abs/2305.08021},

year  = {2023},

date = {2023-07-15},

urldate = {2023-07-15},

booktitle = {International Conference on Machine Learning (ICML)},

keywords = {Dynamic networks, Edge AI, Featured, Internet of Things, Model Compression \& Optimization, Neural Architecture Search},

pubstate = {published},

tppubtype = {conference}

}

@conference{MIDL2023,

title = {Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentation},

author = {Rahman, Md Mostafijur and Marculescu, Radu},

url = {https://arxiv.org/abs/2303.16892},

year  = {2023},

date = {2023-07-10},

urldate = {2023-07-10},

booktitle = {Medical Imaging with Deep Learning},

keywords = {Deep Learning Architecture, Medical Image Segmentation, Vision Transformer},

pubstate = {published},

tppubtype = {conference}

}

@conference{mobileViG,

title = {MobileViG: Graph-Based Sparse Attention for Mobile  Vision Applications},

author = {Munir, Mustafa and Avery, William and Marculescu, Radu},

url = {https://arxiv.org/abs/2307.00395



https://openaccess.thecvf.com/content/CVPR2023W/MobileAI/papers/Munir_MobileViG_Graph-Based_Sparse_Attention_for_Mobile_Vision_Applications_CVPRW_2023_paper.pdf



},

doi = {10.1109/CVPRW59228.2023.00215},

year  = {2023},

date = {2023-06-18},

urldate = {2023-06-18},

booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},

keywords = {Deep Learning Architecture, Edge AI, Internet of Things},

pubstate = {published},

tppubtype = {conference}

}