Debiased Cross Contrastive Quantization for Unsupervised Image Retrieval

Contrastive quantization (applying vector quantization to contrastive learning) has achieved great success in large-scale image retrieval because of its advantage of high computational efficiency and small storage space. This article designs a novel optimization framework to simultaneously optimize the cross quantization and the debiased contrastive learning, termed Debiased Cross Contrastive Quantization (DCCQ). The proposed framework is implemented in an end-to-end network, resulting in both reduced quantization error and deletion of many false negative samples. Specifically, to increase the distinguishability between codewords, DCCQ introduces the codeword similarity loss and soft quantization entropy loss for network training. Furthermore, the memory bank strategy and multi-crop image augmentation strategy are employed to promote the effectiveness and efficiency of contrastive learning. Extensive experiments on three large-scale real image benchmark datasets show that the proposed DCCQ yields state-of-the-art results.