no code implementations • 28 Mar 2024 • Moein Heidari, Reza Azad, Sina Ghorbani Kolahi, René Arimond, Leon Niggemeier, Alaa Sulaiman, Afshin Bozorgpour, Ehsan Khodapanah Aghdam, Amirhossein Kazerouni, Ilker Hacihaliloglu, Dorit Merhof
Intrigued by the inherent ability of the human visual system to identify salient regions in complex scenes, attention mechanisms have been seamlessly integrated into various Computer Vision (CV) tasks.
1 code implementation • 31 Aug 2023 • Reza Azad, Leon Niggemeier, Michael Huttemann, Amirhossein Kazerouni, Ehsan Khodapanah Aghdam, Yury Velichko, Ulas Bagci, Dorit Merhof
To address these challenges, we introduce the concept of \textbf{Deformable Large Kernel Attention (D-LKA Attention)}, a streamlined attention mechanism employing large convolution kernels to fully appreciate volumetric context.
1 code implementation • 31 Aug 2023 • Reza Azad, Amirhossein Kazerouni, Babak Azad, Ehsan Khodapanah Aghdam, Yury Velichko, Ulas Bagci, Dorit Merhof
Vision Transformer (ViT) models have demonstrated a breakthrough in a wide range of computer vision tasks.
2 code implementations • 25 Aug 2023 • Reza Azad, Amirhossein Kazerouni, Alaa Sulaiman, Afshin Bozorgpour, Ehsan Khodapanah Aghdam, Abin Jose, Dorit Merhof
Furthermore, to intensify the importance of the boundary information, we impose an additional attention map by creating a Gaussian pyramid on top of the HF components.
1 code implementation • 25 Jan 2023 • Reza Azad, Yiwei Jia, Ehsan Khodapanah Aghdam, Julien Cohen-Adad, Dorit Merhof
(3) In contrast to a bridge that only contains token-wise self-attention, we propose a Dual Transformer Bridge that also includes channel-wise self-attention to exploit correlations between scales at different stages from a dual perspective.
1 code implementation • 9 Jan 2023 • Reza Azad, Amirhossein Kazerouni, Moein Heidari, Ehsan Khodapanah Aghdam, Amirali Molaei, Yiwei Jia, Abin Jose, Rijo Roy, Dorit Merhof
The remarkable performance of the Transformer architecture in natural language processing has recently also triggered broad interest in Computer Vision.
1 code implementation • 27 Dec 2022 • Reza Azad, René Arimond, Ehsan Khodapanah Aghdam, Amirhossein Kazerouni, Dorit Merhof
Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies.
1 code implementation • 27 Nov 2022 • Reza Azad, Ehsan Khodapanah Aghdam, Amelie Rauland, Yiwei Jia, Atlas Haddadi Avval, Afshin Bozorgpour, Sanaz Karimijafarbigloo, Joseph Paul Cohen, Ehsan Adeli, Dorit Merhof
U-Net is the most widespread image segmentation architecture due to its flexibility, optimized modular design, and success in all medical image modalities.
1 code implementation • 14 Nov 2022 • Amirhossein Kazerouni, Ehsan Khodapanah Aghdam, Moein Heidari, Reza Azad, Mohsen Fayyaz, Ilker Hacihaliloglu, Dorit Merhof
Then, we provide a systematic taxonomy of diffusion models in the medical domain and propose a multi-perspective categorization based on their application, imaging modality, organ of interest, and algorithms.
1 code implementation • 30 Oct 2022 • Ehsan Khodapanah Aghdam, Reza Azad, Maral Zarvani, Dorit Merhof
We argue that the classical concatenation operation utilized in the skip connection path can be further improved by incorporating an attention mechanism.
1 code implementation • 1 Aug 2022 • Reza Azad, Moein Heidari, Moein Shariatnia, Ehsan Khodapanah Aghdam, Sanaz Karimijafarbigloo, Ehsan Adeli, Dorit Merhof
Especially, deep neural networks based on seminal architectures such as U-shaped models with skip-connections or atrous convolution with pyramid pooling have been tailored to a wide range of medical image analysis tasks.
1 code implementation • 18 Jul 2022 • Moein Heidari, Amirhossein Kazerouni, Milad Soltany, Reza Azad, Ehsan Khodapanah Aghdam, Julien Cohen-Adad, Dorit Merhof
In this paper, we propose HiFormer, a novel method that efficiently bridges a CNN and a transformer for medical image segmentation.