Nested Hash Layer: A Plug-and-play Module for Multiple-length Hash Code Learning

ICLR 2026 Conference Submission18023 Authors

Keywords: deep hashing, image retrieval, efficient search

Abstract: Deep supervised hashing is essential for efficient storage and search in large-scale image retrieval. Traditional models generate hash codes of a single length, but this creates a trade-off between efficiency and effectiveness for different code lengths. To find the optimal length for a task, multiple models must be trained, increasing time and computation. Furthermore, relationships between hash codes of different lengths are often ignored. To address these issues, we propose the Nested Hash Layer (NHL), a plug-and-play module for deep supervised hashing models. NHL generates hash codes of multiple lengths simultaneously in a nested structure. To resolve optimization conflicts from multiple learning objectives, we introduce a dominance-aware dynamic weighting strategy to adjust gradients. Additionally, we propose a long-short cascade self-distillation method, where long hash codes guide the learning of shorter ones, improving overall code quality. Experiments indicate that the NHL achieves an overall training speed improvement of approximately 5 to 8 times across various deep supervised hashing models and enhances the average performance of these models by about 3.4%.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 18023