paper-with-me

홈 › Papers

A Closer Look at Self-Supervised Lightweight Vision Transformers

2022-05-28 · Shaoru Wang, Jin Gao, Zeming Li, Xiaoqin Zhang, Weiming Hu

Self-supervised learning on large-scale Vision Transformers (ViTs) as pre-training methods has achieved promising downstream performance. Yet, how much these pre-training paradigms promote lightweight ViTs' performance is considerably less studied. In this work, we develop and benchmark several self-supervised pre-training methods on image classification tasks and some downstream dense prediction tasks. We surprisingly find that if proper pre-training is adopted, even vanilla lightweight ViTs show comparable performance to previous SOTA networks with delicate architecture design. It breaks the recently popular conception that vanilla ViTs are not suitable for vision tasks in lightweight regimes. We also point out some defects of such pre-training, e.g., failing to benefit from large-scale pre-training data and showing inferior performance on data-insufficient downstream tasks. Furthermore, we analyze and clearly show the effect of such pre-training by analyzing the properties of the layer representation and attention maps for related models. Finally, based on the above analyses, a distillation strategy during pre-training is developed, which leads to further downstream performance improvement for MAE-based pre-training. Code is available at https://github.com/wangsr126/mae-lite.

📄 PDF Abstract BibTeX arXiv:2205.14443

Code (2)

wangsr126/mae-lite 공식 구현 pytorch
lianqi1008/mcm pytorch

Tasks

Contrastive Learningimage-classificationImage ClassificationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision

2022-07-11 · Lanxiao Li, Michael Heizmann

Self-supervised pre-training for 3D vision has drawn increasing research interest in recent years. In order to learn informative representations, a lot of previous works exploit invariances of 3D features, e.g., perspect…

Contrastive Learningobject-detectionObject Detection

A Closer Look at Few-Shot Out-of-Distribution Intent Detection

2022-10-01 · COLING 2022 10 · Li-Ming Zhan, Haowen Liang, Lu Fan, Xiao-Ming Wu 외

We consider few-shot out-of-distribution (OOD) intent detection, a practical and important problem for the development of task-oriented dialogue systems. Despite its importance, this problem is seldom studied in the lite…

Intent DetectionTask-Oriented Dialogue Systems

Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning

2021-06-05 · Martin Q. Ma, Yao-Hung Hubert Tsai, Paul Pu Liang, Han Zhao 외

Contrastive self-supervised learning (SSL) learns an embedding space that maps similar data pairs closer and dissimilar data pairs farther apart. Despite its success, one issue has been overlooked: the fairness aspect of…

AttributeContrastive LearningFairnessRepresentation Learning+1

SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs

2022-03-02 · Xiao Liu, Haoyun Hong, Xinghao Wang, Zeyi Chen 외

Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing Web-scale KGs. Over the course of its development, the label supervision has bee…

Entity AlignmentKnowledge GraphsSelf-Supervised Learning

A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classification

2024-07-16 · Markus Marks, Manuel Knott, Neehar Kondapaneni, Elijah Cole 외

Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. The model is forced to learn about the data structure or context by solv…

BenchmarkingFew-Shot Learningimage-classificationImage Classification+1