Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing

arXiv:2403.06071v1 Announce Type: new
Abstract: Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent advancements in the field demonstrate that employing large-scale backbones (e.g., ViT) in unsupervised semantic hashing models can yield substantial improvements. However, the inference delay has become increasingly difficult to overlook. Knowledge distillation provides a means for practical model compression to alleviate this delay. Nevertheless, the prevailing knowledge distillation …

arxiv cs.cv cs.ir distillation hashing knowledge robust semantic type unsupervised