Deep self-enhancement hashing for robust multi-label cross-modal retrieval

Published: 01 Jan 2024, Last Modified: 11 Apr 2025Pattern Recognit. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•The non-convex random linear combinations of features help construct pseudo-OOD data.•Features produced by the prototype-based auto-encoder enhance the OOD discriminative.•Constraining the maximum distance of dissimilar codes improves the OOD robustness.
Loading