English
Related papers

Related papers: Adaptive Layer Selection for Efficient Vision Tran…

200 papers

We propose and demonstrate an alternating Fourier and image domain filtering approach for feature extraction as an efficient alternative to build a vision backbone without using the computationally intensive attention. The performance among…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Yunling Zheng , Zeyi Xu , Fanghui Xue , Biao Yang , Jiancheng Lyu , Shuai Zhang , Yingyong Qi , Jack Xin

Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve…

Computation and Language · Computer Science 2024-06-05 Bowen Zhao , Hannaneh Hajishirzi , Qingqing Cao

Vision transformers (ViTs) have demonstrated remarkable performance across various visual tasks. However, ViT models suffer from substantial computational and memory requirements, making it challenging to deploy them on resource-constrained…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Navin Ranjan , Andreas Savakis

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…

As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many…

Computer Vision and Pattern Recognition · Computer Science 2024-02-06 Otniel-Bogdan Mercea , Alexey Gritsenko , Cordelia Schmid , Anurag Arnab

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Qiankun Ma , Ziyao Zhang , Haofei Wang , Jie Chen , Zhen Song , Hairong Zheng

Current state-of-the-art results in computer vision depend in part on fine-tuning large pre-trained vision models. However, with the exponential growth of model sizes, the conventional full fine-tuning, which needs to store a individual…

Computer Vision and Pattern Recognition · Computer Science 2023-08-01 Shibo Jie , Haoqing Wang , Zhi-Hong Deng

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Anxhelo Diko , Danilo Avola , Marco Cascio , Luigi Cinque

Finetuning can be used to tackle domain-specific tasks by transferring knowledge. Previous studies on finetuning focused on adapting only the weights of a task-specific classifier or re-optimizing all layers of the pre-trained model using…

Machine Learning · Computer Science 2023-01-18 Basel Barakat , Qiang Huang

This paper tackles the problem of efficient video recognition. In this area, video transformers have recently dominated the efficiency (top-1 accuracy vs FLOPs) spectrum. At the same time, there have been some attempts in the image domain…

Computer Vision and Pattern Recognition · Computer Science 2022-08-24 Adrian Bulat , Brais Martinez , Georgios Tzimiropoulos

Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. Yet, the demand for individualized and comprehensive fine-tuning processes for each task entails substantial…

Computer Vision and Pattern Recognition · Computer Science 2024-05-16 Weifeng Lin , Ziheng Wu , Wentao Yang , Mingxin Huang , Jun Huang , Lianwen Jin

Extensive work has demonstrated the effectiveness of Vision Transformers. The plain Vision Transformer tends to obtain multi-scale features by selecting fixed layers, or the last layer of features aiming to achieve higher performance in…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Fangjian Lin , Yizhe Ma , Shengwei Tian

Hybrid vision transformers combine the elements of conventional neural networks (NN) and vision transformers (ViT) to enable lightweight and accurate detection. However, several challenges remain for their efficient deployment on…

Hardware Architecture · Computer Science 2025-07-22 Joren Dumoulin , Pouya Houshmand , Vikram Jain , Marian Verhelst

Vision Transformers (ViTs) have triggered the most recent and significant breakthroughs in computer vision. Their efficient designs are mostly guided by the indirect metric of computational complexity, i.e., FLOPs, which however has a clear…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Zizheng Pan , Jianfei Cai , Bohan Zhuang

Transformers, composed of multiple self-attention layers, hold strong promises toward a generic learning primitive applicable to different data modalities, including the recent breakthroughs in computer vision achieving state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Sayak Paul , Pin-Yu Chen

Adapting vision transformer foundation models through parameter-efficient fine-tuning (PEFT) methods has become increasingly popular. These methods optimize a limited subset of parameters, enabling efficient adaptation without the need to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Son Thai Ly , Hien V. Nguyen

Why are state-of-the-art Vision Transformers (ViTs) not designed to exploit natural geometric symmetries such as 90-degree rotations and reflections? In this paper, we argue that there is no fundamental reason, and what has been missing is…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 David Nordström , Johan Edstedt , Fredrik Kahl , Georg Bökman

The rapid advancements in vision-language models (VLMs), such as CLIP, have intensified the need to address distribution shifts between training and testing datasets. Although prior Test-Time Training (TTT) techniques for VLMs have…

Computer Vision and Pattern Recognition · Computer Science 2025-02-05 Yuto Kojima , Jiarui Xu , Xueyan Zou , Xiaolong Wang

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision…

Computer Vision and Pattern Recognition · Computer Science 2024-08-23 Anwei Luo , Rizhao Cai , Chenqi Kong , Yakun Ju , Xiangui Kang , Jiwu Huang , Alex C. Kot

Visual Instruction Finetuning (VIF) is pivotal for post-training Vision-Language Models (VLMs). Unlike unimodal instruction finetuning in plain-text large language models, which mainly requires instruction datasets to enable model…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Jucheng Hu , Suorong Yang , Dongzhan Zhou
‹ Prev 1 8 9 10 Next ›