HHF: Hashing-guided Hinge Function For Deep Hashing Retrieval

Abstract

Deep hashing has shown promising performance in large-scale image retrieval. However, latent codes extracted by Deep Neural Networks (DNNs) will inevitably lose semantic information during the binarization process, which damages the retrieval accuracy and makes it challenging. Although many existing approaches perform regularization to alleviate quantization errors, we figure out an incompatible conflict between metric learning and quantization learning. The metric loss penalizes the inter-class distances to push different classes unconstrained far away. Worse still, it tends to map the latent code deviate from ideal binarization point and generate severe ambiguity in the binarization process. Based on the minimum distance of the binary linear code, we creatively propose Hashing-guided Hinge Function (HHF) to avoid such conflict. In detail, the carefully-designed inflection point, which relies on the hash bit length and category numbers, is explicitly adopted to balance the metric term

Stats

• citations39
• S2 citations—
• github stars12
• HF likes0
• heat score14.24
• arxiv keyxu2021hhf

Related papers

• Deep Hashing Via Householder Quantization (2023)0.00
• Unsupervised Semantic Deep Hashing (2018)10.48
• Binary Constrained Deep Hashing Network For Image Retrieval Without Manual Annotation (2018)5.84
• Deep Asymmetric Hashing With Dual Semantic Regression And Class Structure Quantization (2021)6.77
• Deep Hashing With Semantic Hash Centers For Image Retrieval (2025)2.26
• Compact Hash Code Learning With Binary Deep Neural Network (2017)9.03
• Deep Class-wise Hashing: Semantics-preserving Hashing Via Class-wise Loss (2018)11.19
• Dual Asymmetric Deep Hashing Learning (2018)9.03