Learning Binary Hash Codes Based on Adaptable Label Representations

Huei‐Fang Yang

doi:10.1109/TNNLS.2021.3095399

2022-11-01

PRE

Huei‐Fang Yang

Cheng-Hao Tu

Chu‐Song Chen *

DOI：10.1109/TNNLS.2021.3095399

原文链接

原文求助

摘要

En 中文

The goal of supervised hashing is to construct hash mappings from collections of images and semantic annotations such that semantically relevant images are embedded nearby in the learned binary hash representations. Existing deep supervised hashing approaches that employ classification frameworks with a classification training objective for learning hash codes often encode class labels as one-hot or multi-hot vectors. We argue that such label encodings do not well reflect semantic relations among classes and instead, effective class label representations ought to be learned from data, which could provide more discriminative signals for hashing. In this article, we introduce Adaptive Labeling Deep Hashing (AdaLabelHash) that learns binary hash codes based on learnable class label representations. We treat the class labels as the vertices of a K-dimensional hypercube, which are trainable variables and adapted together with network weights during the backward network training procedure. The label representations, referred to as codewords, are the target outputs of hash mapping learning. In the label space, semantically relevant images are then expressed by the codewords that are nearby regarding Hamming distances, yielding compact and discriminative binary hash representations. Furthermore, we find that the learned label representations well reflect semantic relations. Our approach is easy to realize and can simultaneously construct both the label representations and the compact binary embeddings. Quantitative and qualitative evaluations on several popular benchmarks validate the superiority of AdaLabelHash in learning effective binary codes for image search.

Keyword:

Semantics

Training

Binary codes

Hash functions

Quantization (signal)

Encoding

Standards

Binary codes

deep learning

hashing

image retrieval