English
Related papers

Related papers: Learning Spatial Decay for Vision Transformers

200 papers

Using images acquired by different satellite sensors has shown to improve classification performance in the framework of crop mapping from satellite image time series (SITS). Existing state-of-the-art architectures use self-attention…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Theresa Follath , David Mickisch , Jan Hemmerling , Stefan Erasmi , Marcel Schwieder , Begüm Demir

Recently, linear complexity sequence modeling networks have achieved modeling capabilities similar to Vision Transformers on a variety of computer vision tasks, while using fewer FLOPs and less memory. However, their advantage in terms of…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Bencheng Liao , Xinggang Wang , Lianghui Zhu , Qian Zhang , Chang Huang

Recent advances in Vision Transformers (ViTs) have significantly advanced semantic segmentation performance. However, their adaptation to new target domains remains challenged by distribution shifts, which often disrupt global attention…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Enming Zhang , Zhengyu Li , Yanru Wu , Jingge Wang , Yang Tan , Guan Wang , Yang Li , Xiaoping Zhang

This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductive biases into their architectures, the plain ViT suffers…

Computer Vision and Pattern Recognition · Computer Science 2023-02-14 Zhe Chen , Yuchen Duan , Wenhai Wang , Junjun He , Tong Lu , Jifeng Dai , Yu Qiao

Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Dong Lao , Yangchao Wu , Tian Yu Liu , Alex Wong , Stefano Soatto

Vision Transformers (ViTs) are becoming more popular and dominating technique for various vision tasks, compare to Convolutional Neural Networks (CNNs). As a demanding technique in computer vision, ViTs have been successfully solved various…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Khawar Islam

Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Yuanduo Hong , Huihui Pan , Weichao Sun , Xinghu Yu , Huijun Gao

Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network (CNN), has received much attention. Recent work showed that ViTs are also vulnerable to adversarial examples like CNNs. To build robust ViTs, an intuitive…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Boxi Wu , Jindong Gu , Zhifeng Li , Deng Cai , Xiaofei He , Wei Liu

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Ali Hatamizadeh , Jiaming Song , Guilin Liu , Jan Kautz , Arash Vahdat

We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space…

Robotics · Computer Science 2022-05-27 Stefan Wapnick , Travis Manderson , David Meger , Gregory Dudek

Vision Transformers (ViT) have advanced computer vision, yet their efficacy in complex tasks like driving remains less explored. This study enhances ViT by integrating human eye gaze, captured via eye-tracking, to increase prediction…

Computer Vision and Pattern Recognition · Computer Science 2025-01-13 Sharath Koorathota , Nikolas Papadopoulos , Jia Li Ma , Shruti Kumar , Xiaoxiao Sun , Arunesh Mittal , Patrick Adelman , Paul Sajda

As transformers are equivariant to the permutation of input tokens, encoding the positional information of tokens is necessary for many tasks. However, since existing positional encoding schemes have been initially designed for NLP tasks,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Takeru Miyato , Bernhard Jaeger , Max Welling , Andreas Geiger

The aim of this work is to explore the potential of pre-trained vision-language models, e.g. Vision Transformers (ViT), enhanced with advanced data augmentation strategies for the detection of AI-generated images. Our approach leverages a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Shrikant Malviya , Neelanjan Bhowmik , Stamos Katsigiannis

Visual Geometry Grounded Transformer (VGGT) delivers state-of-the-art feed-forward 3D reconstruction, yet its global self-attention layer suffers from a drastic collapse phenomenon when the input sequence exceeds a few hundred frames:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Huan Li , Longjun Luo , Yuling Shi , Xiaodong Gu

Visual search is important in our daily life. The efficient allocation of visual attention is critical to effectively complete visual search tasks. Prior research has predominantly modelled the spatial allocation of visual attention in…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Yini Fang , Jingling Yu , Haozheng Zhang , Ralf van der Lans , Bertram Shi

Recently, Transformer-based architecture has been introduced into single image deraining task due to its advantage in modeling non-local information. However, existing approaches tend to integrate global features based on a dense…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Zhentao Fan , Hongming Chen , Yufeng Li

We present PAT, a transformer-based network that learns complex temporal co-occurrence action dependencies in a video by exploiting multi-scale temporal features. In existing methods, the self-attention mechanism in transformers loses the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Faegheh Sardari , Armin Mustafa , Philip J. B. Jackson , Adrian Hilton

Loss of plasticity refers to the progressive inability of a model to adapt to new tasks and poses a fundamental challenge for continual learning. While this phenomenon has been extensively studied in homogeneous neural architectures, such…

Machine Learning · Computer Science 2026-03-10 Caihao Sun , Mingqi Yuan , Shiyuan Wang , Jiayu Chen

Triggered by the success of transformers in various visual tasks, the spatial self-attention mechanism has recently attracted more and more attention in the computer vision community. However, we empirically found that a typical vision…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Jiayin Sun , Hong Wang , Qiulei Dong

We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter forecast horizons reaching a stationary and often implausible…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Emre Aksan , Manuel Kaufmann , Peng Cao , Otmar Hilliges