Distributed Zero-Shot Learning for Visual Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911259426816000 |
|---|---|
| author | Chen, Zhi Luo, Yadan Huang, Zi Li, Jingjing Wang, Sen Yu, Xin |
| author_facet | Chen, Zhi Luo, Yadan Huang, Zi Li, Jingjing Wang, Sen Yu, Xin |
| contents | In this paper, we propose a Distributed Zero-Shot Learning (DistZSL) framework that can fully exploit decentralized data to learn an effective model for unseen classes. Considering the data heterogeneity issues across distributed nodes, we introduce two key components to ensure the effective learning of DistZSL: a cross-node attribute regularizer and a global attribute-to-visual consensus. Our proposed cross-node attribute regularizer enforces the distances between attribute features to be similar across different nodes. In this manner, the overall attribute feature space would be stable during learning, and thus facilitate the establishment of visual-to-attribute(V2A) relationships. Then, we introduce the global attribute-tovisual consensus to mitigate biased V2A mappings learned from individual nodes. Specifically, we enforce the bilateral mapping between the attribute and visual feature distributions to be consistent across different nodes. Thus, the learned consistent V2A mapping can significantly enhance zero-shot learning across different nodes. Extensive experiments demonstrate that DistZSL achieves superior performance to the state-of-the-art in learning from distributed data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08170 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Distributed Zero-Shot Learning for Visual Recognition Chen, Zhi Luo, Yadan Huang, Zi Li, Jingjing Wang, Sen Yu, Xin Computer Vision and Pattern Recognition In this paper, we propose a Distributed Zero-Shot Learning (DistZSL) framework that can fully exploit decentralized data to learn an effective model for unseen classes. Considering the data heterogeneity issues across distributed nodes, we introduce two key components to ensure the effective learning of DistZSL: a cross-node attribute regularizer and a global attribute-to-visual consensus. Our proposed cross-node attribute regularizer enforces the distances between attribute features to be similar across different nodes. In this manner, the overall attribute feature space would be stable during learning, and thus facilitate the establishment of visual-to-attribute(V2A) relationships. Then, we introduce the global attribute-tovisual consensus to mitigate biased V2A mappings learned from individual nodes. Specifically, we enforce the bilateral mapping between the attribute and visual feature distributions to be consistent across different nodes. Thus, the learned consistent V2A mapping can significantly enhance zero-shot learning across different nodes. Extensive experiments demonstrate that DistZSL achieves superior performance to the state-of-the-art in learning from distributed data. |
| title | Distributed Zero-Shot Learning for Visual Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.08170 |