Self-Guided Masked Autoencoder
Masked Autoencoder (MAE) is a self-supervised approach for representation learning, widely applicable to a variety of downstream tasks in computer vision. In spite of its success, it is still not fully uncovered what and how MAE exactly learns. In this paper, with an in-depth analysis, we discover that MAE intrinsically learns pattern-based patch-level clustering from surprisingly early stages of pretraining. Upon this understanding, we propose self-guided masked autoencoder, which internally generates informed mask by utilizing its progress in patch clustering, substituting the naive random masking of the vanilla MAE. Our approach significantly boosts its learning process without relying on any external models or supplementary information, keeping the benefit of self-supervised nature of MAE intact. Comprehensive experiments on various downstream tasks verify the effectiveness of the proposed method.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSimilar Papers 제목 키워드 기반
Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-tr…
Molecular Property PredictionProperty PredictionSelf-Supervised LearningFeature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing
Self-supervised learning guided by masked image modelling, such as Masked AutoEncoder (MAE), has attracted wide attention for pretraining vision transformers in remote sensing. However, MAE tends to excessively focus on …
Image ClassificationMulti-Label Image ClassificationSelf-Supervised LearningThe Dynamic Duo of Collaborative Masking and Target for Advanced Masked Autoencoder Learning
Masked autoencoders (MAE) have recently succeeded in self-supervised vision representation learning. Previous work mainly applied custom-designed (e.g., random, block-wise) masking or teacher (e.g., CLIP)-guided masking …
DecoderRepresentation LearningDownstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimization
Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked one…
InformativenessRepresentation LearningA Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond
Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, genera…
Contrastive LearningDenoisingSelf-Supervised Learning