Direct Coloring for Self-Supervised Enhanced Feature Decoupling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916504354684928 |
|---|---|
| author | Mohamadi, Salman Doretto, Gianfranco Adjeroh, Donald A. |
| author_facet | Mohamadi, Salman Doretto, Gianfranco Adjeroh, Donald A. |
| contents | The success of self-supervised learning (SSL) has been the focus of multiple recent theoretical and empirical studies, including the role of data augmentation (in feature decoupling) as well as complete and dimensional representation collapse. While complete collapse is well-studied and addressed, dimensional collapse has only gain attention and addressed in recent years mostly using variants of redundancy reduction (aka whitening) techniques. In this paper, we further explore a complementary approach to whitening via feature decoupling for improved representation learning while avoiding representation collapse. In particular, we perform feature decoupling by early promotion of useful features via careful feature coloring. The coloring technique is developed based on a Bayesian prior of the augmented data, which is inherently encoded for feature decoupling. We show that our proposed framework is complementary to the state-of-the-art techniques, while outperforming both contrastive and recent non-contrastive methods. We also study the different effects of coloring approach to formulate it as a general complementary technique along with other baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02109 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Direct Coloring for Self-Supervised Enhanced Feature Decoupling Mohamadi, Salman Doretto, Gianfranco Adjeroh, Donald A. Computer Vision and Pattern Recognition The success of self-supervised learning (SSL) has been the focus of multiple recent theoretical and empirical studies, including the role of data augmentation (in feature decoupling) as well as complete and dimensional representation collapse. While complete collapse is well-studied and addressed, dimensional collapse has only gain attention and addressed in recent years mostly using variants of redundancy reduction (aka whitening) techniques. In this paper, we further explore a complementary approach to whitening via feature decoupling for improved representation learning while avoiding representation collapse. In particular, we perform feature decoupling by early promotion of useful features via careful feature coloring. The coloring technique is developed based on a Bayesian prior of the augmented data, which is inherently encoded for feature decoupling. We show that our proposed framework is complementary to the state-of-the-art techniques, while outperforming both contrastive and recent non-contrastive methods. We also study the different effects of coloring approach to formulate it as a general complementary technique along with other baselines. |
| title | Direct Coloring for Self-Supervised Enhanced Feature Decoupling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.02109 |