Deep Hash Distillation for Image Retrieval. (arXiv:2112.08816v2 [cs.CV] UPDATED)

In hash-based image retrieval systems, degraded or transformed inputs usually
generate different codes from the original, deteriorating the retrieval
accuracy. To mitigate this issue, data augmentation can be applied during
training. However, even if augmented samples of an image are similar in real
feature space, the quantization can scatter them far away in Hamming space.
This results in representation discrepancies that can impede training and
degrade performance. In this work, we propose a novel self-distilled hashing
scheme to minimize the …

arxiv cv distillation hash image retrieval