English
Related papers

Related papers: DeiT-LT Distillation Strikes Back for Vision Trans…

200 papers

Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge distillation to improve the generalization ability of CNN models…

Computer Vision and Pattern Recognition · Computer Science 2020-08-04 Bingchen Zhao , Xin Wen

In recent years, the rapid expansion of dataset sizes and the increasing complexity of deep learning models have significantly escalated the demand for computational resources, both for data storage and model training. Dataset distillation…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Zhe Li , Hadrien Reynaud , Mischa Dombrowski , Sarah Cechnicka , Franciskus Xaverius Erick , Bernhard Kainz

The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Shuoxi Zhang , Hanpeng Liu , Stephen Lin , Kun He

Dataset distillation reduces the network training cost by synthesizing small and informative datasets from large-scale ones. Despite the success of the recent dataset distillation algorithms, three drawbacks still limit their wider…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Kai Wang , Jianyang Gu , Daquan Zhou , Zheng Zhu , Wei Jiang , Yang You

Non-autoregressive machine translation (NAT) systems predict a sequence of output tokens in parallel, achieving substantial improvements in generation speed compared to autoregressive models. Existing NAT models usually rely on the…

Computation and Language · Computer Science 2021-02-24 Chunting Zhou , Graham Neubig , Jiatao Gu

Feature-map knowledge distillation (KD) transfers internal representations well between comparably sized Vision Transformers (ViTs), but it often fails in compression. We revisit this failure and uncover a paradox. Sample-wise SVD shows…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Huiyuan Tian , Bonan Xu , Shijian Li

Neuroimaging of large populations is valuable to identify factors that promote or resist brain disease, and to assist diagnosis, subtyping, and prognosis. Data-driven models such as convolutional neural networks (CNNs) have increasingly…

Image and Video Processing · Electrical Eng. & Systems 2023-03-16 Nikhil J. Dhinagar , Sophia I. Thomopoulos , Emily Laltoo , Paul M. Thompson

Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the \textit{extremely simple}…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Jin Gao , Shubo Lin , Shaoru Wang , Yutong Kou , Zeming Li , Liang Li , Congxuan Zhang , Xiaoqin Zhang , Yizheng Wang , Weiming Hu

Large vision Transformers (ViTs) driven by self-supervised pre-training mechanisms achieved unprecedented progress. Lightweight ViT models limited by the model capacity, however, benefit little from those pre-training mechanisms. Knowledge…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Wei Huang , Zhiliang Peng , Li Dong , Furu Wei , Jianbin Jiao , Qixiang Ye

Open-vocabulary dense prediction tasks including object detection and image segmentation have been advanced by the success of Contrastive Language-Image Pre-training (CLIP). CLIP models, particularly those incorporating vision transformers…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Size Wu , Wenwei Zhang , Lumin Xu , Sheng Jin , Xiangtai Li , Wentao Liu , Chen Change Loy

The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 George Cazenavette , Antonio Torralba , Vincent Sitzmann

Few-shot model compression aims to compress a large model into a more compact one with only a tiny training set (even without labels). Block-level pruning has recently emerged as a leading technique in achieving high accuracy and low…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Hanxiao Zhang , Yifan Zhou , Guo-Hua Wang , Jianxin Wu

Dataset distillation aims to synthesize a small, information-rich dataset from a large one for efficient model training. However, existing dataset distillation methods struggle with long-tailed datasets, which are prevalent in real-world…

Machine Learning · Computer Science 2025-03-20 Zhenghao Zhao , Haoxuan Wang , Yuzhang Shang , Kai Wang , Yan Yan

In recent computer vision research, the advent of the Vision Transformer (ViT) has rapidly revolutionized various architectural design efforts: ViT achieved state-of-the-art image classification performance using self-attention found in…

Computer Vision and Pattern Recognition · Computer Science 2023-01-13 Yuki Tatsunami , Masato Taki

Despite exciting progress in pre-training for visual-linguistic (VL) representations, very few aspire to a small VL model. In this paper, we study knowledge distillation (KD) to effectively compress a transformer-based large VL model into a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Zhiyuan Fang , Jianfeng Wang , Xiaowei Hu , Lijuan Wang , Yezhou Yang , Zicheng Liu

The Vision Transformer (ViT) has made significant strides in the field of computer vision. However, as the depth of the model and the resolution of the input images increase, the computational cost associated with training and running ViT…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Xinfeng Zhao , Yaoru Sun

Dataset distillation methods reduce large-scale datasets to smaller sets of synthetic data, preserving sufficient information to quickly train a new model from scratch. However, prior work on dataset distillation has focused exclusively on…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Xindi Wu , Byron Zhang , Zhiwei Deng , Olga Russakovsky

Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Sihao Lin , Hongwei Xie , Bing Wang , Kaicheng Yu , Xiaojun Chang , Xiaodan Liang , Gang Wang

In this paper, we question if well pre-trained vision transformer (ViT) models could be used as teachers that exhibit scalable properties to advance cross architecture knowledge distillation (KD) research, in the context of using…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Jiawei Fan , Chao Li , Xiaolong Liu , Anbang Yao

The Vision Transformer (ViT) architecture has recently achieved competitive performance across a variety of computer vision tasks. One of the motivations behind ViTs is weaker inductive biases, when compared to convolutional neural networks…

Computer Vision and Pattern Recognition · Computer Science 2021-12-20 Akash Umakantha , Joao D. Semedo , S. Alireza Golestaneh , Wan-Yi S. Lin