paper-with-me

Papers

Improvements to Self-Supervised Representation Learning for Masked Image Modeling

2022-05-21 · Jiawei Mao, Xuesong Yin, Yuanqi Chang, Honggu Zhou

This paper explores improvements to the masked image modeling (MIM) paradigm. The MIM paradigm enables the model to learn the main object features of the image by masking the input image and predicting the masked part by the unmasked part. We found the following three main directions for MIM to be improved. First, since both encoders and decoders contribute to representation learning, MIM uses only encoders for downstream tasks, which ignores the impact of decoders on representation learning. Although the MIM paradigm already employs small decoders with asymmetric structures, we believe that continued reduction of decoder parameters is beneficial to improve the representational learning capability of the encoder . Second, MIM solves the image prediction task by training the encoder and decoder together , and does not design a separate task for the encoder . To further enhance the performance of the encoder when performing downstream tasks, we designed the encoder for the tasks of comparative learning and token position prediction. Third, since the input image may contain background and other objects, and the proportion of each object in the image varies, reconstructing the tokens related to the background or to other objects is not meaningful for MIM to understand the main object representations. Therefore we use ContrastiveCrop to crop the input image so that the input image contains as much as possible only the main objects. Based on the above three improvements to MIM, we propose a new model, Contrastive Masked AutoEncoders (CMAE). We achieved a Top-1 accuracy of 65.84% on tinyimagenet using the ViT-B backbone, which is +2.89 outperforming the MAE of competing methods when all conditions are equal. Code will be made available.

📄 PDF Abstract BibTeX arXiv:2205.10546

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderRepresentation Learning

Methods 이 논문이 사용한 방법론

MAE 설명 없음
MIM 설명 없음

Similar Papers 제목 키워드 기반

Understanding Self-Supervised Pretraining with Part-Aware Representation Learning

2023-01-27 · Jie Zhu, Jiyang Qi, Mingyu Ding, Xiaokang Chen 외

In this paper, we are interested in understanding self-supervised pretraining through studying the capability that self-supervised representation pretraining methods learn part-aware representations. The study is mainly …

Contrastive LearningObjectRepresentation Learning

Masked Siamese Networks for Label-Efficient Learning

2022-04-14 · Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski 외

We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the representation of an image view containing randomly masked patches to the repres…

image-classificationImage ClassificationSelf-Supervised Image ClassificationSelf-Supervised Learning+1

MPS-AMS: Masked Patches Selection and Adaptive Masking Strategy Based Self-Supervised Medical Image Segmentation

2023-02-27 · Xiangtao Wang, Ruizhi Wang, Biao Tian, Jiaojiao Zhang 외

Existing self-supervised learning methods based on contrastive learning and masked image modeling have demonstrated impressive performances. However, current masked image modeling methods are mainly utilized in natural i…

Contrastive LearningImage SegmentationMedical Image SegmentationSegmentation+2

Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training

2023-12-05 · CVPR 2024 1 · Arun Reddy, William Paul, Corban Rivera, Ketul Shah 외

In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain…

Action RecognitionDomain AdaptationTemporal Action LocalizationUnsupervised Domain Adaptation

Suppressing Non-Semantic Noise in Masked Image Modeling Representations

2026-03-31 · Martine Hjelkrem-Tan, Marius Aasan, Rwiddhi Chakraborty, Gabriel Y. Arteaga 외 arxiv

Masked Image Modeling (MIM) has become a ubiquitous self-supervised vision paradigm. In this work, we show that MIM objectives cause the learned representations to retain non-semantic information, which ultimately hurts …