Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913304977342464 |
|---|---|
| author | Wang, Jinpeng Chen, Bin Zhang, Qiang Meng, Zaiqiao Liang, Shangsong Xia, Shu-Tao |
| author_facet | Wang, Jinpeng Chen, Bin Zhang, Qiang Meng, Zaiqiao Liang, Shangsong Xia, Shu-Tao |
| contents | Deep quantization methods have shown high efficiency on large-scale image retrieval. However, current models heavily rely on ground-truth information, hindering the application of quantization in label-hungry scenarios. A more realistic demand is to learn from inexhaustible uploaded images that are associated with informal tags provided by amateur users. Though such sketchy tags do not obviously reveal the labels, they actually contain useful semantic information for supervising deep quantization. To this end, we propose Weakly-Supervised Deep Hyperspherical Quantization (WSDHQ), which is the first work to learn deep quantization from weakly tagged images. Specifically, 1) we use word embeddings to represent the tags and enhance their semantic information based on a tag correlation graph. 2) To better preserve semantic information in quantization codes and reduce quantization error, we jointly learn semantics-preserving embeddings and supervised quantizer on hypersphere by employing a well-designed fusion layer and tailor-made loss functions. Extensive experiments show that WSDHQ can achieve state-of-art performance on weakly-supervised compact coding. Code is available at https://github.com/gimpong/AAAI21-WSDHQ. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_04998 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval Wang, Jinpeng Chen, Bin Zhang, Qiang Meng, Zaiqiao Liang, Shangsong Xia, Shu-Tao Computer Vision and Pattern Recognition Artificial Intelligence Information Retrieval Deep quantization methods have shown high efficiency on large-scale image retrieval. However, current models heavily rely on ground-truth information, hindering the application of quantization in label-hungry scenarios. A more realistic demand is to learn from inexhaustible uploaded images that are associated with informal tags provided by amateur users. Though such sketchy tags do not obviously reveal the labels, they actually contain useful semantic information for supervising deep quantization. To this end, we propose Weakly-Supervised Deep Hyperspherical Quantization (WSDHQ), which is the first work to learn deep quantization from weakly tagged images. Specifically, 1) we use word embeddings to represent the tags and enhance their semantic information based on a tag correlation graph. 2) To better preserve semantic information in quantization codes and reduce quantization error, we jointly learn semantics-preserving embeddings and supervised quantizer on hypersphere by employing a well-designed fusion layer and tailor-made loss functions. Extensive experiments show that WSDHQ can achieve state-of-art performance on weakly-supervised compact coding. Code is available at https://github.com/gimpong/AAAI21-WSDHQ. |
| title | Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2404.04998 |