English
Related papers

Related papers: ViTCAE: ViT-based Class-conditioned Autoencoder

200 papers

Vision Transformers (ViTs), when pre-trained on large-scale data, provide general-purpose representations for diverse downstream tasks. However, artifacts in ViTs are widely observed across different supervision paradigms and downstream…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Cheng Shi , Yizhou Yu , Sibei Yang

In this paper, we propose EDIT (Encoder-Decoder Image Transformer), a novel architecture designed to mitigate the attention sink phenomenon observed in Vision Transformer models. Attention sink occurs when an excessive amount of attention…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Wenfeng Feng , Hongxiang Wang , Jianlong Wang , Xin Zhang , Jingjing Zhao , Yueyue Liang , Xiang Chen , Duokui Han

Despite advances in deep probabilistic models, learning discrete latent representations remains challenging. This work introduces a novel method to improve inference in discrete Variational Autoencoders by reframing the inference problem…

Machine Learning · Computer Science 2025-06-11 María Martínez-García , Grace Villacrés , David Mitchell , Pablo M. Olmos

Recently, vision transformers (ViTs) have achieved excellent performance on vision tasks by measuring the global self-attention among the image patches. Given $n$ patches, they will have quadratic complexity such as $\mathcal{O}(n^2)$ and…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Jiquan Shan , Junxiao Wang , Lifeng Zhao , Liang Cai , Hongyuan Zhang , Ioannis Liritzis

In recent years, learned image compression methods have demonstrated superior rate-distortion performance compared to traditional image compression methods. Recent methods utilize convolutional neural networks (CNN), variational…

Computer Vision and Pattern Recognition · Computer Science 2025-02-14 Priyanka Mudgal , Feng Liu

This paper studies the computational offloading of video action recognition in edge computing. To achieve effective semantic information extraction and compression, following semantic communication we propose a novel spatiotemporal…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Nan Li , Mehdi Bennis , Alexandros Iosifidis , Qi Zhang

The use of transformers for vision tasks has challenged the traditional dominant role of convolutional neural networks (CNN) in computer vision (CV). For image classification tasks, Vision Transformer (ViT) effectively establishes spatial…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Shihua Sun , Kenechukwu Nwodo , Shridatt Sugrim , Angelos Stavrou , Haining Wang

Vision Transformers (ViTs) have revolutionized computer vision by leveraging self-attention to model long-range dependencies. However, ViTs face challenges such as high computational costs due to the quadratic scaling of self-attention and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Zhoujie Qian

Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different…

Computation and Language · Computer Science 2020-10-06 Alessandro Raganato , Yves Scherrer , Jörg Tiedemann

Vision Transformers (ViTs) have gained significant popularity in recent years and have proliferated into many applications. However, their behavior under different learning paradigms is not well explored. We compare ViTs trained through…

Computer Vision and Pattern Recognition · Computer Science 2023-04-07 Matthew Walmer , Saksham Suri , Kamal Gupta , Abhinav Shrivastava

The Vision Transformer (ViT) architecture has become widely recognized in computer vision, leveraging its self-attention mechanism to achieve remarkable success across various tasks. Despite its strengths, ViT's optimization remains…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Haoyu Yun , Hamid Krim

Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it…

Computer Vision and Pattern Recognition · Computer Science 2025-05-02 Yao Qiang , Chengyin Li , Prashant Khanduri , Dongxiao Zhu

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Machine Learning · Computer Science 2026-01-14 Zhenglun Kong , Yize Li , Fanhu Zeng , Lei Xin , Shvat Messica , Xue Lin , Pu Zhao , Manolis Kellis , Hao Tang , Marinka Zitnik

Despite the widespread adoption of transformers in medical applications, the exploration of multi-scale learning through transformers remains limited, while hierarchical representations are considered advantageous for computer-aided medical…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Xiaoya Tang , Bodong Zhang , Man Minh Ho , Beatrice S. Knudsen , Tolga Tasdizen

Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images. However, for downstream tasks like semantic classification, the representations learned by VAE are less competitive than…

Machine Learning · Statistics 2022-05-31 Mingtian Zhang , Tim Z. Xiao , Brooks Paige , David Barber

Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work…

Computation and Language · Computer Science 2020-03-31 Zhaojiang Lin , Genta Indra Winata , Peng Xu , Zihan Liu , Pascale Fung

Controllable text generation has taken a gigantic step forward these days. Yet existing methods are either constrained in a one-off pattern or not efficient enough for receiving multiple conditions at every generation stage. We propose a…

Computation and Language · Computer Science 2022-10-10 Haoqin Tu , Zhongliang Yang , Jinshuai Yang , Siyu Zhang , Yongfeng Huang

Recently, Vision Transformers (ViTs) have attracted a lot of attention in the field of computer vision. Generally, the powerful representative capacity of ViTs mainly benefits from the self-attention mechanism, which has a high computation…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Deli Yu , Teng Xi , Jianwei Li , Baopu Li , Gang Zhang , Haocheng Feng , Junyu Han , Jingtuo Liu , Errui Ding , Jingdong Wang

Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Weitai Kang , Luowei Zhou , Junyi Wu , Changchang Sun , Yan Yan

Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks. It leverages extra learnable tokens, known as prompts, which steer the frozen pretrained ViTs. Although VPT has…

Machine Learning · Computer Science 2023-06-09 Seungryong Yoo , Eunji Kim , Dahuin Jung , Jungbeom Lee , Sungroh Yoon
‹ Prev 1 3 4 5 6 7 10 Next ›