Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval
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_ | 1866911910707855360 |
|---|---|
| author | Ma, Yiwei Sun, Xiaoshuai Ji, Jiayi Jiang, Guannan Zhuang, Weilin Ji, Rongrong |
| author_facet | Ma, Yiwei Sun, Xiaoshuai Ji, Jiayi Jiang, Guannan Zhuang, Weilin Ji, Rongrong |
| contents | Text-based person retrieval (TPR) is a challenging task that involves retrieving a specific individual based on a textual description. Despite considerable efforts to bridge the gap between vision and language, the significant differences between these modalities continue to pose a challenge. Previous methods have attempted to align text and image samples in a modal-shared space, but they face uncertainties in optimization directions due to the movable features of both modalities and the failure to account for one-to-many relationships of image-text pairs in TPR datasets. To address this issue, we propose an effective bi-directional one-to-many embedding paradigm that offers a clear optimization direction for each sample, thus mitigating the optimization problem. Additionally, this embedding scheme generates multiple features for each sample without introducing trainable parameters, making it easier to align with several positive samples. Based on this paradigm, we propose a novel Bi-directional one-to-many Embedding Alignment (Beat) model to address the TPR task. Our experimental results demonstrate that the proposed Beat model achieves state-of-the-art performance on three popular TPR datasets, including CUHK-PEDES (65.61 R@1), ICFG-PEDES (58.25 R@1), and RSTPReID (48.10 R@1). Furthermore, additional experiments on MS-COCO, CUB, and Flowers datasets further demonstrate the potential of Beat to be applied to other image-text retrieval tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05620 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval Ma, Yiwei Sun, Xiaoshuai Ji, Jiayi Jiang, Guannan Zhuang, Weilin Ji, Rongrong Computer Vision and Pattern Recognition Text-based person retrieval (TPR) is a challenging task that involves retrieving a specific individual based on a textual description. Despite considerable efforts to bridge the gap between vision and language, the significant differences between these modalities continue to pose a challenge. Previous methods have attempted to align text and image samples in a modal-shared space, but they face uncertainties in optimization directions due to the movable features of both modalities and the failure to account for one-to-many relationships of image-text pairs in TPR datasets. To address this issue, we propose an effective bi-directional one-to-many embedding paradigm that offers a clear optimization direction for each sample, thus mitigating the optimization problem. Additionally, this embedding scheme generates multiple features for each sample without introducing trainable parameters, making it easier to align with several positive samples. Based on this paradigm, we propose a novel Bi-directional one-to-many Embedding Alignment (Beat) model to address the TPR task. Our experimental results demonstrate that the proposed Beat model achieves state-of-the-art performance on three popular TPR datasets, including CUHK-PEDES (65.61 R@1), ICFG-PEDES (58.25 R@1), and RSTPReID (48.10 R@1). Furthermore, additional experiments on MS-COCO, CUB, and Flowers datasets further demonstrate the potential of Beat to be applied to other image-text retrieval tasks. |
| title | Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.05620 |