Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912008783265792 |
|---|---|
| author | Dai, Fengyuan Huang, Siteng Zhang, Min Gong, Biao Wang, Donglin |
| author_facet | Dai, Fengyuan Huang, Siteng Zhang, Min Gong, Biao Wang, Donglin |
| contents | To transfer knowledge from seen attribute-object compositions to recognize unseen ones, recent compositional zero-shot learning (CZSL) methods mainly discuss the optimal classification branches to identify the elements, leading to the popularity of employing a three-branch architecture. However, these methods mix up the underlying relationship among the branches, in the aspect of consistency and diversity. Specifically, consistently providing the highest-level features for all three branches increases the difficulty in distinguishing classes that are superficially similar. Furthermore, a single branch may focus on suboptimal regions when spatial messages are not shared between the personalized branches. Recognizing these issues and endeavoring to address them, we propose a novel method called Focus-Consistent Multi-Level Aggregation (FOMA). Our method incorporates a Multi-Level Feature Aggregation (MFA) module to generate personalized features for each branch based on the image content. Additionally, a Focus-Consistent Constraint encourages a consistent focus on the informative regions, thereby implicitly exchanging spatial information between all branches. Extensive experiments on three benchmark datasets (UT-Zappos, C-GQA, and Clothing16K) demonstrate that our FOMA outperforms SOTA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_17083 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning Dai, Fengyuan Huang, Siteng Zhang, Min Gong, Biao Wang, Donglin Computer Vision and Pattern Recognition To transfer knowledge from seen attribute-object compositions to recognize unseen ones, recent compositional zero-shot learning (CZSL) methods mainly discuss the optimal classification branches to identify the elements, leading to the popularity of employing a three-branch architecture. However, these methods mix up the underlying relationship among the branches, in the aspect of consistency and diversity. Specifically, consistently providing the highest-level features for all three branches increases the difficulty in distinguishing classes that are superficially similar. Furthermore, a single branch may focus on suboptimal regions when spatial messages are not shared between the personalized branches. Recognizing these issues and endeavoring to address them, we propose a novel method called Focus-Consistent Multi-Level Aggregation (FOMA). Our method incorporates a Multi-Level Feature Aggregation (MFA) module to generate personalized features for each branch based on the image content. Additionally, a Focus-Consistent Constraint encourages a consistent focus on the informative regions, thereby implicitly exchanging spatial information between all branches. Extensive experiments on three benchmark datasets (UT-Zappos, C-GQA, and Clothing16K) demonstrate that our FOMA outperforms SOTA. |
| title | Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.17083 |