Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion Adaptation
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_ | 1866912160311934976 |
|---|---|
| author | Zhu, Jiankun Zhao, Sicheng Jiang, Jing Tang, Wenbo Xu, Zhaopan Han, Tingting Xu, Pengfei Yao, Hongxun |
| author_facet | Zhu, Jiankun Zhao, Sicheng Jiang, Jing Tang, Wenbo Xu, Zhaopan Han, Tingting Xu, Pengfei Yao, Hongxun |
| contents | Visual emotion recognition (VER), which aims at understanding humans' emotional reactions toward different visual stimuli, has attracted increasing attention. Given the subjective and ambiguous characteristics of emotion, annotating a reliable large-scale dataset is hard. For reducing reliance on data labeling, domain adaptation offers an alternative solution by adapting models trained on labeled source data to unlabeled target data. Conventional domain adaptation methods require access to source data. However, due to privacy concerns, source emotional data may be inaccessible. To address this issue, we propose an unexplored task: source-free domain adaptation (SFDA) for VER, which does not have access to source data during the adaptation process. To achieve this, we propose a novel framework termed Bridge then Begin Anew (BBA), which consists of two steps: domain-bridged model generation (DMG) and target-related model adaptation (TMA). First, the DMG bridges cross-domain gaps by generating an intermediate model, avoiding direct alignment between two VER datasets with significant differences. Then, the TMA begins training the target model anew to fit the target structure, avoiding the influence of source-specific knowledge. Extensive experiments are conducted on six SFDA settings for VER. The results demonstrate the effectiveness of BBA, which achieves remarkable performance gains compared with state-of-the-art SFDA methods and outperforms representative unsupervised domain adaptation approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_13577 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion Adaptation Zhu, Jiankun Zhao, Sicheng Jiang, Jing Tang, Wenbo Xu, Zhaopan Han, Tingting Xu, Pengfei Yao, Hongxun Computer Vision and Pattern Recognition Artificial Intelligence Visual emotion recognition (VER), which aims at understanding humans' emotional reactions toward different visual stimuli, has attracted increasing attention. Given the subjective and ambiguous characteristics of emotion, annotating a reliable large-scale dataset is hard. For reducing reliance on data labeling, domain adaptation offers an alternative solution by adapting models trained on labeled source data to unlabeled target data. Conventional domain adaptation methods require access to source data. However, due to privacy concerns, source emotional data may be inaccessible. To address this issue, we propose an unexplored task: source-free domain adaptation (SFDA) for VER, which does not have access to source data during the adaptation process. To achieve this, we propose a novel framework termed Bridge then Begin Anew (BBA), which consists of two steps: domain-bridged model generation (DMG) and target-related model adaptation (TMA). First, the DMG bridges cross-domain gaps by generating an intermediate model, avoiding direct alignment between two VER datasets with significant differences. Then, the TMA begins training the target model anew to fit the target structure, avoiding the influence of source-specific knowledge. Extensive experiments are conducted on six SFDA settings for VER. The results demonstrate the effectiveness of BBA, which achieves remarkable performance gains compared with state-of-the-art SFDA methods and outperforms representative unsupervised domain adaptation approaches. |
| title | Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion Adaptation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2412.13577 |