English
Related papers

Related papers: MABViT -- Modified Attention Block Enhances Vision…

200 papers

Recently, the joint learning framework (JOINT) integrates matching based transductive reasoning and online inductive learning to achieve accurate and robust semi-supervised video object segmentation (SVOS). However, using the mask embedding…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Meng Lan , Jing Zhang , Lefei Zhang , Dacheng Tao

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Zizheng Pan , Bohan Zhuang , Haoyu He , Jing Liu , Jianfei Cai

In the field of image clustering, the widely used contrastive learning networks improve clustering performance by maximizing the similarity between positive pairs and the dissimilarity of negative pairs of the inputs. Extant contrastive…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Cheng Wang , Shuisheng Zhou , Fengjiao Peng , Jin Sheng , Feng Ye , Yinli Dong

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Zhuofan Xia , Xuran Pan , Shiji Song , Li Erran Li , Gao Huang

An appropriate choice of the activation function (like ReLU, sigmoid or swish) plays an important role in the performance of (deep) multilayer perceptrons (MLP) for classification and regression learning. Prototype-based classification…

Machine Learning · Computer Science 2019-01-21 Thomas Villmann , John Ravichandran , Andrea Villmann , David Nebel , Marika Kaden

Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance. However, one significant drawback of ViTs is their…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Kaixin Xu , Zhe Wang , Chunyun Chen , Xue Geng , Jie Lin , Mohamed M. Sabry Aly , Xulei Yang , Min Wu , Xiaoli Li , Weisi Lin

Element-wise activation functions play a critical role in deep neural networks via affecting the expressivity power and the learning dynamics. Learning-based activation functions have recently gained increasing attention and success. We…

Machine Learning · Computer Science 2020-10-05 Dengsheng Chen , Jun Li , Kai Xu

Previous research observed accuracy degradation when replacing the attention softmax with a point-wise activation such as ReLU. In the context of vision transformers, we find that this degradation is mitigated when dividing by sequence…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Mitchell Wortsman , Jaehoon Lee , Justin Gilmer , Simon Kornblith

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Zhuofan Xia , Xuran Pan , Shiji Song , Li Erran Li , Gao Huang

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Machine Learning · Computer Science 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li

Multi-head attention is a driving force behind state-of-the-art transformers, which achieve remarkable performance across a variety of natural language processing (NLP) and computer vision tasks. It has been observed that for many…

Machine Learning · Computer Science 2022-06-14 Tam Nguyen , Tan M. Nguyen , Dung D. Le , Duy Khuong Nguyen , Viet-Anh Tran , Richard G. Baraniuk , Nhat Ho , Stanley J. Osher

Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention retains quadratic complexity, making them computationally…

Machine Learning · Computer Science 2026-05-26 Chunyuan Deng , Yizhe Zhang , Rui-Jie Zhu , Yuanyuan Xu , Jiarui Liu , T. S. Eugene Ng , Hanjie Chen

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Wayner Barrios , SouYoung Jin

The deployment of Vision Transformers (ViTs) on hardware platforms, specially Field-Programmable Gate Arrays (FPGAs), presents many challenges, which are mainly due to the substantial computational and power requirements of their non-linear…

Computer Vision and Pattern Recognition · Computer Science 2024-08-19 Mohammad Erfan Sadeghi , Arash Fayyazi , Seyedarmin Azizi , Massoud Pedram

Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and…

Computer Vision and Pattern Recognition · Computer Science 2022-01-26 Pranav Jeevan , Amit sethi

This paper presents a new model architecture, gate with inhibition MLP (giMLP).The gate with inhibition on CycleMLP (gi-CycleMLP) can produce equal performance on the ImageNet classification task, and it also improves the BERT, Roberta, and…

Computation and Language · Computer Science 2022-08-03 Cheng Kang , Jindich Prokop , Lei Tong , Huiyu Zhou , Yong Hu , Daneil Novak

Traditional vision transformer consists of two parts: transformer encoder and multi-layer perception (MLP). The former plays the role of feature learning to obtain better representation, while the latter plays the role of classification.…

Image and Video Processing · Electrical Eng. & Systems 2024-01-11 Jichen Yang , Fangfan Chen , Rohan Kumar Das , Zhengyu Zhu , Shunsi Zhang

The Vision Transformer (ViT) has made significant advancements in computer vision, utilizing self-attention mechanisms to achieve state-of-the-art performance across various tasks, including image classification, object detection, and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Sehyeong Jo , Gangjae Jang , Haesol Park

The transformer architecture is widely used in machine learning models and consists of two alternating sublayers: attention heads and MLPs. We prove that an MLP neuron can be implemented by a masked attention head with internal dimension 1…

Machine Learning · Computer Science 2023-09-18 Robert Huben , Valerie Morris

Multi-modal large language models (MLLMs) have made significant strides in various visual understanding tasks. However, the majority of these models are constrained to process low-resolution images, which limits their effectiveness in…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Xiangyu Zhao , Xiangtai Li , Haodong Duan , Haian Huang , Yining Li , Kai Chen , Hua Yang