Transformer-Based Person Search with High-Frequency Augmentation and Multi-Wave Mixing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916815478718464 |
|---|---|
| author | Shu, Qilin Zhang, Qixian Zhang, Qi Zhang, Hongyun Miao, Duoqian Zhao, Cairong |
| author_facet | Shu, Qilin Zhang, Qixian Zhang, Qi Zhang, Hongyun Miao, Duoqian Zhao, Cairong |
| contents | The person search task aims to locate a target person within a set of scene images. In recent years, transformer-based models in this field have made some progress. However, they still face three primary challenges: 1) the self-attention mechanism tends to suppress high-frequency components in the features, which severely impacts model performance; 2) the computational cost of transformers is relatively high. To address these issues, we propose a novel High-frequency Augmentation and Multi-Wave mixing (HAMW) method for person search. HAMW is designed to enhance the discriminative feature extraction capabilities of transformers while reducing computational overhead and improving efficiency. Specifically, we develop a three-stage framework that progressively optimizes both detection and re-identification performance. Our model enhances the perception of high-frequency features by learning from augmented inputs containing additional high-frequency components. Furthermore, we replace the self-attention layers in the transformer with a strategy based on multi-level Haar wavelet fusion to capture multi-scale features. This not only lowers the computational complexity but also alleviates the suppression of high-frequency features and enhances the ability to exploit multi-scale information. Extensive experiments demonstrate that HAMW achieves state-of-the-art performance on both the CUHK-SYSU and PRW datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23202 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transformer-Based Person Search with High-Frequency Augmentation and Multi-Wave Mixing Shu, Qilin Zhang, Qixian Zhang, Qi Zhang, Hongyun Miao, Duoqian Zhao, Cairong Computer Vision and Pattern Recognition The person search task aims to locate a target person within a set of scene images. In recent years, transformer-based models in this field have made some progress. However, they still face three primary challenges: 1) the self-attention mechanism tends to suppress high-frequency components in the features, which severely impacts model performance; 2) the computational cost of transformers is relatively high. To address these issues, we propose a novel High-frequency Augmentation and Multi-Wave mixing (HAMW) method for person search. HAMW is designed to enhance the discriminative feature extraction capabilities of transformers while reducing computational overhead and improving efficiency. Specifically, we develop a three-stage framework that progressively optimizes both detection and re-identification performance. Our model enhances the perception of high-frequency features by learning from augmented inputs containing additional high-frequency components. Furthermore, we replace the self-attention layers in the transformer with a strategy based on multi-level Haar wavelet fusion to capture multi-scale features. This not only lowers the computational complexity but also alleviates the suppression of high-frequency features and enhances the ability to exploit multi-scale information. Extensive experiments demonstrate that HAMW achieves state-of-the-art performance on both the CUHK-SYSU and PRW datasets. |
| title | Transformer-Based Person Search with High-Frequency Augmentation and Multi-Wave Mixing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.23202 |