Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910628616077312 |
|---|---|
| author | Maitra, Arkadip Mitra, Shree Manna, Siladittya Bhattacharya, Saumik Pal, Umapada |
| author_facet | Maitra, Arkadip Mitra, Shree Manna, Siladittya Bhattacharya, Saumik Pal, Umapada |
| contents | Self-supervised learning has developed rapidly over the last decade and has been applied in many areas of computer vision. Decorrelation-based self-supervised pretraining has shown great promise among non-contrastive algorithms, yielding performance at par with supervised and contrastive self-supervised baselines. In this work, we explore the decorrelation-based paradigm of self-supervised learning and apply the same to learning disentangled stroke features for writer identification. Here we propose a modified formulation of the decorrelation-based framework named SWIS which was proposed for signature verification by standardizing the features along each dimension on top of the existing framework. We show that the proposed framework outperforms the contemporary self-supervised learning framework on the writer identification benchmark and also outperforms several supervised methods as well. To the best of our knowledge, this work is the first of its kind to apply self-supervised learning for learning representations for writer verification tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01441 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification Maitra, Arkadip Mitra, Shree Manna, Siladittya Bhattacharya, Saumik Pal, Umapada Computer Vision and Pattern Recognition Self-supervised learning has developed rapidly over the last decade and has been applied in many areas of computer vision. Decorrelation-based self-supervised pretraining has shown great promise among non-contrastive algorithms, yielding performance at par with supervised and contrastive self-supervised baselines. In this work, we explore the decorrelation-based paradigm of self-supervised learning and apply the same to learning disentangled stroke features for writer identification. Here we propose a modified formulation of the decorrelation-based framework named SWIS which was proposed for signature verification by standardizing the features along each dimension on top of the existing framework. We show that the proposed framework outperforms the contemporary self-supervised learning framework on the writer identification benchmark and also outperforms several supervised methods as well. To the best of our knowledge, this work is the first of its kind to apply self-supervised learning for learning representations for writer verification tasks. |
| title | Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.01441 |