2026
16.
Munir, Mustafa; Rahman, Md Mostafijur; Marculescu, Radu
AdaptViG: Adaptive Vision GNN with Exponential Decay Gating Conference Forthcoming
2026 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2026), Forthcoming.
Links | BibTeX | Tags: Deep Learning, Deep Learning Architecture, Efficient AI, Featured, Graph Neural Network
@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://arxiv.org/abs/2511.09942},
year = {2026},
date = {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 = {forthcoming},
tppubtype = {conference}
}
2025
15.
Munir, Mustafa; Rahman, Md Mostafijur; Wei, Xiwen; Yang, Yuedong; Marculescu, Radu
SearchViG: Optimal Vision GNNs via Ramanujan Spectral Optimization Conference Forthcoming
The Fourth Learning on Graphs Conference (LOG 2025), Forthcoming.
Links | BibTeX | Tags: Deep Learning, Deep Learning Architecture, Dynamic networks, Efficient AI, Featured, Graph Neural Network
@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},
booktitle = {The Fourth Learning on Graphs Conference (LOG 2025)},
keywords = {Deep Learning, Deep Learning Architecture, Dynamic networks, Efficient AI, Featured, Graph Neural Network},
pubstate = {forthcoming},
tppubtype = {conference}
}
14.
Munir, Mustafa; Zhang, Alex; Marculescu, Radu
VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation Conference
Proceedings of the International Conference on Computer Vision (ICCV 2025) Workshops, 2025.
Abstract | Links | BibTeX | Tags: Deep Learning Architecture, Efficient AI, Featured, Lightweight Architecture, Model Compression & Optimization
@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}
}
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.
13.
Gedik, Hakan Emre; Martin, Andrew; Munir, Mustafa; Baser, Oguzhan; Marculescu, Radu; Chinchali, Sandeep P.; Bovik, Alan C.
AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs Technical Report
2025.
Links | BibTeX | Tags: Deep Learning, Deep Learning Architecture, Efficient AI, Graph Neural Network
@techreport{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 = {2025},
date = {2025-09-29},
keywords = {Deep Learning, Deep Learning Architecture, Efficient AI, Graph Neural Network},
pubstate = {published},
tppubtype = {techreport}
}
12.
Rahman, Md Mostafijur; Munir, Mustafa; Marculescu, Radu
EfficientMedNeXt: Multi-Receptive Dilated Convolutions for Medical Image Segmentation Conference
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025.
Abstract | Links | BibTeX | Tags: 3D Segmentation, Deep Learning Architecture, Efficient AI, Efficient Inference, Featured, Medical Image Segmentation
@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}
}
In this work, we introduce EfficientMedNeXt—a 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.
11.
Munir, Mustafa; Li, Guihong; Rahman, Md Mostafijur; Zhang, Alex; Marculescu, Radu
From Data to Design: Leveraging Frequency Statistics for Efficient Neural Network Architectures Conference
2025 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2025.
Links | BibTeX | Tags: Deep Learning Architecture, Efficient Inference, Model Compression & Optimization, Neural Architecture Search
@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}
}
10.
Rahman, Md Mostafijur; Marculescu, Radu
EffiDec3D: An Optimized Decoder for High-Performance and Efficient 3D Medical Image Segmentation Conference
Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025.
Abstract | Links | BibTeX | Tags: 3D Segmentation, Deep Learning Architecture, Efficient AI, Efficient Decoder, Featured, Medical Image Segmentation
@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}
}
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.
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.
9.
Munir, Mustafa; Rahman, Md Mostafijur; Marculescu, Radu
RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone Conference
2025 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025), 2025.
Links | BibTeX | Tags: Deep Learning Architecture, Edge AI, Efficient Inference, Featured, Model Compression & Optimization
@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}
}
2024
8.
Munir, Mustafa; Zhang, Alex; Marculescu, Radu
Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs Conference
The Third Learning on Graphs Conference (LOG 2024), 2024.
Links | BibTeX | Tags: Deep Learning Architecture, Edge AI, Graph Neural Network
@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}
}
7.
Munir, Mustafa; Avery, William; Rahman, Md Mostafijur; Marculescu, Radu
GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs Conference
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Abstract | Links | BibTeX | Tags: Deep Learning Architecture, Dynamic networks, Edge AI, Efficient Inference, Graph Neural Network
@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}
}
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.
6.
Rahman, Md Mostafijur; Munir, Mustafa; Marculescu, Radu
EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation Conference
Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024.
Abstract | Links | BibTeX | Tags: Deep Learning Architecture, Efficient Decoder, Medical Image Segmentation, Multi-scale Depth-wise Convolutions, Vision Transformer
@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}
}
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.
5.
Avery, William; Munir, Mustafa; Marculescu, Radu
Scaling Graph Convolutions for Mobile Vision Conference
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
Links | BibTeX | Tags: Deep Learning Architecture, Edge AI, Embedded Systems, Internet of Things
@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}
}
4.
Rahman, Md Mostafijur; Marculescu, Radu
G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation Conference
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024.
Links | BibTeX | Tags: Deep Learning Architecture, Graph Neural Network, Medical Image Segmentation
@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}
}
2023
3.
Rahman, Md Mostafijur; Marculescu, Radu
Medical Imaging with Deep Learning, 2023.
Links | BibTeX | Tags: Deep Learning Architecture, Medical Image Segmentation, Vision Transformer
@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}
}
2.
Munir, Mustafa; Avery, William; Marculescu, Radu
MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications Conference
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023.
Links | BibTeX | Tags: Deep Learning Architecture, Edge AI, Internet of Things
@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}
}
1.
Rahman, Md Mostafijur; Marculescu, Radu
Medical Image Segmentation via Cascaded Attention Decoding Proceedings Article
In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 6222-6231, 2023.
Links | BibTeX | Tags: Deep Learning Architecture, Medical Image Segmentation
@inproceedings{cascade,
title = {Medical Image Segmentation via Cascaded Attention Decoding},
author = {Md Mostafijur Rahman and Radu Marculescu},
url = {https://ieeexplore.ieee.org/document/10030763},
year = {2023},
date = {2023-01-03},
urldate = {2023-01-03},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages = {6222-6231},
keywords = {Deep Learning Architecture, Medical Image Segmentation},
pubstate = {published},
tppubtype = {inproceedings}
}
