MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915620991270912 |
|---|---|
| author | Hong, Jingshan Hu, Haigen Zhang, Huihuang Zhou, Qianwei Li, Zhao |
| author_facet | Hong, Jingshan Hu, Haigen Zhang, Huihuang Zhou, Qianwei Li, Zhao |
| contents | In supervised learning, traditional image masking faces two key issues: (i) discarded pixels are underutilized, leading to a loss of valuable contextual information; (ii) masking may remove small or critical features, especially in fine-grained tasks. In contrast, masked image modeling (MIM) has demonstrated that masked regions can be reconstructed from partial input, revealing that even incomplete data can exhibit strong contextual consistency with the original image. This highlights the potential of masked regions as sources of semantic diversity. Motivated by this, we revisit the image masking approach, proposing to treat masked content as auxiliary knowledge rather than ignored. Based on this, we propose MaskAnyNet, which combines masking with a relearning mechanism to exploit both visible and masked information. It can be easily extended to any model with an additional branch to jointly learn from the recomposed masked region. This approach leverages the semantic diversity of the masked regions to enrich features and preserve fine-grained details. Experiments on CNN and Transformer backbones show consistent gains across multiple benchmarks. Further analysis confirms that the proposed method improves semantic diversity through the reuse of masked content. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12480 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning Hong, Jingshan Hu, Haigen Zhang, Huihuang Zhou, Qianwei Li, Zhao Computer Vision and Pattern Recognition Artificial Intelligence In supervised learning, traditional image masking faces two key issues: (i) discarded pixels are underutilized, leading to a loss of valuable contextual information; (ii) masking may remove small or critical features, especially in fine-grained tasks. In contrast, masked image modeling (MIM) has demonstrated that masked regions can be reconstructed from partial input, revealing that even incomplete data can exhibit strong contextual consistency with the original image. This highlights the potential of masked regions as sources of semantic diversity. Motivated by this, we revisit the image masking approach, proposing to treat masked content as auxiliary knowledge rather than ignored. Based on this, we propose MaskAnyNet, which combines masking with a relearning mechanism to exploit both visible and masked information. It can be easily extended to any model with an additional branch to jointly learn from the recomposed masked region. This approach leverages the semantic diversity of the masked regions to enrich features and preserve fine-grained details. Experiments on CNN and Transformer backbones show consistent gains across multiple benchmarks. Further analysis confirms that the proposed method improves semantic diversity through the reuse of masked content. |
| title | MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.12480 |