Webly Supervised Deep Attentive Quantization

Jinpeng Wang, Bin Chen, Tao Dai, Shu-Tao Xia

Abstract

Learning to hash has been widely applied in large-scale image retrieval. Although current deep hashing methods yield state-of-the-art performance, their heavy dependence on groundtruth information actually makes it difficult to deploy in practical applications such as social media. To solve this problem, we propose a novel method termed Webly Supervised Deep Attentive Quantization (WSDAQ), where deep quantization is trained on web images associated with some userprovided weak tags, without consulting any ground-truth labels. Specifically, we design a tag processing module to leverage semantic information of tags so as to better supervised quantization learning. Besides, we propose an end-to-end trainable Attentive Product Quantization Module (APQM) to quantize deep features of images. Furthermore, we use a noise-contrastive estimation loss to train the model from the perspective of contrastive learning. Experiments validate that WSDAQ is superior to state-of-the-art baselines in compact coding trained on weakly-tagged web images.
BibTeX
@inproceedings{wang2021webly,
  author = {Jinpeng Wang and Bin Chen and Tao Dai and Shu-Tao Xia},
  title = {{Webly Supervised Deep Attentive Quantization}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2021},
  doi = {10.1109/icassp39728.2021.9414172},
}

Loading related content...

Figure