One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching. (arXiv:2205.15721v1 [cs.CV])

Image hashing is a principled approximate nearest neighbor approach to find
similar items to a query in a large collection of images. Hashing aims to learn
a binary-output function that maps an image to a binary vector. For optimal
retrieval performance, producing balanced hash codes with low-quantization
error to bridge the gap between the learning stage's continuous relaxation and
the inference stage's discrete quantization is important. However, in the
existing deep supervised hashing methods, coding balance and low-quantization
error are …

arxiv cv hashing loss quantization