English
Related papers

Related papers: Fully Attentional Networks with Self-emerging Toke…

200 papers

Amos et al. (2024) showed that the accuracy of Transformer models in sequence classification can be significantly improved by first pretraining with a masked token prediction objective without external data or augmentation, a procedure…

Machine Learning · Computer Science 2026-05-21 Omar Coser , Loredana Zollo , Paolo Soda , Antonio Orvieto

Vision Transformers (ViTs) have achieved comparable or superior performance than Convolutional Neural Networks (CNNs) in computer vision. This empirical breakthrough is even more remarkable since, in contrast to CNNs, ViTs do not embed any…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Samy Jelassi , Michael E. Sander , Yuanzhi Li

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Linxiang Su

This study demonstrates a cost-effective approach to semantic segmentation using self-supervised vision transformers (SSVT). By freezing the SSVT backbone and training a lightweight segmentation head, our approach effectively utilizes…

Computer Vision and Pattern Recognition · Computer Science 2024-01-24 Seungho Lee , Seoungyoon Kang , Hyunjung Shim

Vision Transformers (ViTs) have been shown to enhance visual recognition through modeling long-range dependencies with multi-head self-attention (MHSA), which is typically formulated as Query-Key-Value computation. However, the attention…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Chongjian Ge , Xiaohan Ding , Zhan Tong , Li Yuan , Jiangliu Wang , Yibing Song , Ping Luo

Recently, the Vision Transformer (ViT), which applied the transformer structure to the image classification task, has outperformed convolutional neural networks. However, the high performance of the ViT results from pre-training using a…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Seung Hoon Lee , Seunghyun Lee , Byung Cheol Song

In this paper, we build upon the weakly-supervised generation mechanism of intermediate attention maps in any convolutional neural networks and disclose the effectiveness of attention modules more straightforwardly to fully exploit their…

Computer Vision and Pattern Recognition · Computer Science 2022-08-31 Duo Li , Qifeng Chen

Supervised learning can learn large representational spaces, which are crucial for handling difficult learning tasks. However, due to the design of the model, classical image classification approaches struggle to generalize to new problems…

Computer Vision and Pattern Recognition · Computer Science 2021-11-16 Safwen Naimi , Rien van Leeuwen , Wided Souidene , Slim Ben Saoud

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Chun-Fu Chen , Quanfu Fan , Rameswar Panda

Weakly Supervised Semantic Segmentation (WSSS) is a challenging problem that has been extensively studied in recent years. Traditional approaches often rely on external modules like Class Activation Maps to highlight regions of interest and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Joelle Hanna , Damian Borth

Multi-modal representation learning by pretraining has become an increasing interest due to its easy-to-use and potential benefit for various Visual-and-Language~(V-L) tasks. However its requirement of large volume and high-quality…

Multimedia · Computer Science 2020-12-09 Jia Guo , Chen Zhu , Yilun Zhao , Heda Wang , Yao Hu , Xiaofei He , Deng Cai

Transformers have emerged as a competitive alternative to convnets in vision tasks, yet they lack the architectural inductive bias of convnets, which may hinder their potential performance. Specifically, Vision Transformers (ViTs) are not…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Hagay Michaeli , Daniel Soudry

Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Junshan Hu , Jialiang Mao , Zhikang Liu , Zhongpu Xia , Peng Jia , Xianpeng Lang

Transformer-based language models such as BERT having 110M+ parameters have revolutionized natural language understanding, yet their internal mechanisms remain largely opaque to researchers and practitioners. Traditional attention-based…

Machine Learning · Computer Science 2026-05-22 Sayantani Ghosh , Rajashik Datta , Amit Kumar Das , Amlan Chakrabarti

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

Vision-Language Models (VLMs) excel at zero-shot inference but often degrade under test-time domain shifts. For this reason, episodic test-time adaptation strategies have recently emerged as powerful techniques for adapting VLMs to a single…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Konstantinos M. Dafnis , Dimitris N. Metaxas

We propose a communication-efficient collaborative inference framework in the domain of edge inference, focusing on the efficient use of vision transformer (ViT) models. The partitioning strategy of conventional collaborative inference…

Signal Processing · Electrical Eng. & Systems 2024-12-10 Jiwoong Im , Nayoung Kwon , Taewoo Park , Jiheon Woo , Jaeho Lee , Yongjune Kim

Visual attention modeling has recently gained momentum in developing visual hierarchies provided by Convolutional Neural Networks. Despite recent successes of feedforward processing on the abstraction of concepts form raw images, the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-23 Mahdi Biparva , John Tsotsos

Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to those from ImageNet-pretrained models, thanks to the training on…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Jieneng Chen , Qihang Yu , Xiaohui Shen , Alan Yuille , Liang-Chieh Chen

Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-02 Jianwei Yang , Chunyuan Li , Pengchuan Zhang , Xiyang Dai , Bin Xiao , Lu Yuan , Jianfeng Gao