English
Related papers

Related papers: Auto-scaling Vision Transformers without Training

200 papers

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Tianxiao Zhang , Wenju Xu , Bo Luo , Guanghui Wang

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

Test-Time Training (TTT) has recently emerged as a promising direction for efficient sequence modeling. TTT reformulates attention operation as an online learning problem, constructing a compact inner model from key-value pairs at test…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Dongchen Han , Yining Li , Tianyu Li , Zixuan Cao , Ziming Wang , Jun Song , Yu Cheng , Bo Zheng , Gao Huang

In this paper, we present an innovative approach to self-supervised learning for Vision Transformers (ViTs), integrating local masked image modeling with progressive layer freezing. This method focuses on enhancing the efficiency and speed…

Computer Vision and Pattern Recognition · Computer Science 2023-12-06 Utku Mert Topcuoglu , Erdem Akagündüz

In this paper, we investigate the continual learning of Vision Transformers (ViT) for the challenging exemplar-free scenario, with special focus on how to efficiently distill the knowledge of its crucial self-attention mechanism (SAM). Our…

Computer Vision and Pattern Recognition · Computer Science 2022-05-06 Francesco Pelosin , Saurav Jha , Andrea Torsello , Bogdan Raducanu , Joost van de Weijer

This paper investigates the Neural Tangent Kernel (NTK) to search vision transformers without training. In contrast with the previous observation that NTK-based metrics can effectively predict CNNs performance at initialization, we…

Computer Vision and Pattern Recognition · Computer Science 2024-05-09 Qiqi Zhou , Yichen Zhu

Vision transformer (ViT) and its variants have swept through visual learning leaderboards and offer state-of-the-art accuracy in tasks such as image classification, object detection, and semantic segmentation by attending to different parts…

Computer Vision and Pattern Recognition · Computer Science 2023-09-07 Eric Youn , Sai Mitheran J , Sanjana Prabhu , Siyuan Chen

Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues: the massive…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Haoyu He , Jianfei Cai , Jing Liu , Zizheng Pan , Jing Zhang , Dacheng Tao , Bohan Zhuang

Current approaches for designing self-explainable models (SEMs) require complicated training procedures and specific architectures which makes them impractical. With the advance of general purpose foundation models based on Vision…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Kristoffer Wickstrøm , Teresa Dorszewski , Siyan Chen , Michael Kampffmeyer , Elisabeth Wetzer , Robert Jenssen

Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. However, when it comes to handling long token sequences, especially in dense prediction tasks that require…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Jin Li , Yaoming Wang , Xiaopeng Zhang , Bowen Shi , Dongsheng Jiang , Chenglin Li , Wenrui Dai , Hongkai Xiong , Qi Tian

Recent state-of-the-art performances of Vision Transformers (ViT) in computer vision tasks demonstrate that a general-purpose architecture, which implements long-range self-attention, could replace the local feature learning operations of…

Skin lesion segmentation (SLS) plays an important role in skin lesion analysis. Vision transformers (ViTs) are considered an auspicious solution for SLS, but they require more training data compared to convolutional neural networks (CNNs)…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 Siyi Du , Nourhan Bayasi , Ghassan Hamarneh , Rafeef Garbi

We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks. To tackle this problem, we propose a new SSL pipeline, consisting of first…

Computer Vision and Pattern Recognition · Computer Science 2022-08-12 Zhaowei Cai , Avinash Ravichandran , Paolo Favaro , Manchen Wang , Davide Modolo , Rahul Bhotika , Zhuowen Tu , Stefano Soatto

While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the architecture and configuration, such as sampling the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Song Zhang , Qingzhong Wang , Jiang Bian , Haoyi Xiong

Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, but their performance is compromised when applied to unseen domains. Previous methods either engage in prompt learning during the training…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Yunbei Zhang , Akshay Mehra , Jihun Hamm

In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this…

Computer Vision and Pattern Recognition · Computer Science 2021-05-25 Mathilde Caron , Hugo Touvron , Ishan Misra , Hervé Jégou , Julien Mairal , Piotr Bojanowski , Armand Joulin

Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation. However, the high computational requirements of ViTs hinder their widespread…

Computer Vision and Pattern Recognition · Computer Science 2024-05-20 Jemin Lee , Yongin Kwon , Sihyeong Park , Misun Yu , Jeman Park , Hwanjun Song

The Vision Transformer (ViT) excels in global modeling but faces deployment challenges on resource-constrained devices due to the quadratic computational complexity of its attention mechanism. To address this, we propose the Semantic-Aware…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Youbing Hu , Yun Cheng , Anqi Lu , Dawei Wei , Zhijun Li

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

Computer Vision and Pattern Recognition · Computer Science 2023-07-07 Xiangcheng Liu , Tianyi Wu , Guodong Guo

Vision Transformers (ViTs) achieve state-of-the-art segmentation accuracy but require large training datasets because each layer has unique parameters that must be learned independently. We present RD-ViT, a Recurrent-Depth Vision…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Renjie He
‹ Prev 1 4 5 6 7 8 10 Next ›