Multi-label contrastive hashing

Published: 01 Jan 2024, Last Modified: 13 Nov 2024Pattern Recognit. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Multi-level similarity is modeled in supervised contrastive learning to hash.•We design a curriculum strategy to adaptively adjust the weight of quantization loss.•Our approach outperforms several state-of-the-art solutions on three benchmarks.
Loading