English
Related papers

Related papers: Large Separable Kernel Attention: Rethinking the L…

200 papers

Window-based transformers have demonstrated outstanding performance in super-resolution tasks due to their adaptive modeling capabilities through local self-attention (SA). However, they exhibit higher computational complexity and inference…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Zhenyu Hu , Wanjie Sun

Linear RNNs with gating recently demonstrated competitive performance compared to Transformers in language modeling. Although their linear compute scaling in sequence length offers theoretical runtime advantages over Transformers, realizing…

Machine Learning · Computer Science 2025-12-30 Maximilian Beck , Korbinian Pöppel , Phillip Lippe , Sepp Hochreiter

This paper proposes the paradigm of large convolutional kernels in designing modern Convolutional Neural Networks (ConvNets). We establish that employing a few large kernels, instead of stacking multiple smaller ones, can be a superior…

Computer Vision and Pattern Recognition · Computer Science 2024-10-11 Yiyuan Zhang , Xiaohan Ding , Xiangyu Yue

Video super-resolution, which attempts to reconstruct high-resolution video frames from their corresponding low-resolution versions, has received increasingly more attention in recent years. Most existing approaches opt to use deformable…

Computer Vision and Pattern Recognition · Computer Science 2020-10-02 Xuan Xu , Xin Xiong , Jinge Wang , Xin Li

Multi-headed Attention's (MHA) quadratic compute and linearly growing KV-cache make long-context transformers expensive to train and serve. Prior works such as Grouped Query Attention (GQA) and Multi-Latent Attention (MLA) shrink the cache,…

Computation and Language · Computer Science 2026-03-18 Tomas Figliolia , Nicholas Alonso , Rishi Iyer , Quentin Anthony , Beren Millidge

Convolutional Neural Networks (CNNs), architectures consisting of convolutional layers, have been the standard choice in vision tasks. Recent studies have shown that Vision Transformers (VTs), architectures based on self-attention modules,…

Computer Vision and Pattern Recognition · Computer Science 2022-01-24 Kishaan Jeeveswaran , Senthilkumar Kathiresan , Arnav Varma , Omar Magdy , Bahram Zonooz , Elahe Arani

Recent developments in Transformers for language modeling have opened new areas of research in computer vision. Results from late 2019 showed vast performance increases in both object detection and recognition when convolutions are replaced…

Computer Vision and Pattern Recognition · Computer Science 2020-04-21 Jerrod Parker , Shakti Kumar , Joe Roussy

Nowadays, transformer networks have demonstrated superior performance in many computer vision tasks. In a multi-view 3D reconstruction algorithm following this paradigm, self-attention processing has to deal with intricate image tokens…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Liying Yang , Zhenwei Zhu , Xuxin Lin , Jian Nong , Yanyan Liang

Large convolutional neural network models have recently demonstrated impressive performance on video attention prediction. Conventionally, these models are with intensive computation and large memory. To address these issues, we design an…

Computer Vision and Pattern Recognition · Computer Science 2020-01-03 Kui Fu , Peipei Shi , Yafei Song , Shiming Ge , Xiangju Lu , Jia Li

The attention mechanism has gained significant recognition in the field of computer vision due to its ability to effectively enhance the performance of deep neural networks. However, existing methods often struggle to effectively utilize…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Wei Xu , Yi Wan

Brain tumor segmentation models have aided diagnosis in recent years. However, they face MRI complexity and variability challenges, including irregular shapes and unclear boundaries, leading to noise, misclassification, and incomplete…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Ruoxin Wang , Tianyi Tang , Haiming Du , Yuxuan Cheng , Yu Wang , Lingjie Yang , Xiaohui Duan , Yunfang Yu , Yu Zhou , Donglong Chen

Visual token reduction lowers inference costs caused by extensive image features in large vision-language models (LVLMs). Unlike relevant studies that prune tokens in self-attention-only LVLMs, our work uniquely addresses…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Jewon Lee , Ki-Ung Song , Seungmin Yang , Donguk Lim , Jaeyeon Kim , Wooksu Shin , Bo-Kyeong Kim , Yong Jae Lee , Tae-Ho Kim

Vision Transformers have achieved impressive performance in many vision tasks. While the token mixer or attention block has been studied in great detail, much less research has been devoted to the channel mixer or feature mixing block (FFN…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Deepak Sridhar , Yunsheng Li , Nuno Vasconcelos

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…

Computation and Language · Computer Science 2026-04-17 Zeng You , Yaofo Chen , Qiuwu Chen , Ying Sun , Shuhai Zhang , Yingjian Li , Yaowei Wang , Mingkui Tan

Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the width (number of channels) of CNNs, resulting in limited…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Yinpeng Chen , Xiyang Dai , Mengchen Liu , Dongdong Chen , Lu Yuan , Zicheng Liu

Convolutions (Convs) and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. Although some works try to integrate both, they apply the two operators simultaneously at the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Lei Zhu , Xinjiang Wang , Wayne Zhang , Rynson W. H. Lau

Despite the rapid evolution of training paradigms, the decoder backbone of large vision--language models (LVLMs) remains fundamentally rooted in the residual-connection Transformer architecture. Therefore, deciphering the distinct roles of…

Artificial Intelligence · Computer Science 2026-05-08 Gongli Xi , Ye Tian , Mengyu Yang , Huahui Yi , Liang Lin , Xiaoshuai Hao , Kun Wang , Wendong Wang

Accurate medical image segmentation is essential for diagnosis and treatment planning of diseases. Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they are…

Image and Video Processing · Electrical Eng. & Systems 2020-11-05 Ran Gu , Guotai Wang , Tao Song , Rui Huang , Michael Aertsen , Jan Deprest , Sébastien Ourselin , Tom Vercauteren , Shaoting Zhang

Motivated by the increasing popularity of attention mechanisms, we observe that popular convolutional (conv.) attention models like Squeeze-and-Excite (SE) and Convolutional Block Attention Module (CBAM) rely on expensive multi-layer…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Majedaldein Almahasneh , Xianghua Xie , Adeline Paiement

Convolutional neural networks (CNNs) have been not only widespread but also achieved noticeable results on numerous applications including image classification, restoration, and generation. Although the weight-sharing property of…

Computer Vision and Pattern Recognition · Computer Science 2022-09-15 Min-Cheol Sagong , Yoon-Jae Yeo , Seung-Won Jung , Sung-Jea Ko