Self-Guided Masked Autoencoder
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918104838176768 |
|---|---|
| author | Shin, Jeongwoo Lee, Inseo Lee, Junho Lee, Joonseok |
| author_facet | Shin, Jeongwoo Lee, Inseo Lee, Junho Lee, Joonseok |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19773 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Guided Masked Autoencoder Shin, Jeongwoo Lee, Inseo Lee, Junho Lee, Joonseok Computer Vision and Pattern Recognition 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. |
| title | Self-Guided Masked Autoencoder |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.19773 |