Push For Quantization: Deep Fisher Hashing

Abstract

Current massive datasets demand light-weight access for analysis. Discrete hashing methods are thus beneficial because they map high-dimensional data to compact binary codes that are efficient to store and process, while preserving semantic similarity. To optimize powerful deep learning methods for image hashing, gradient-based methods are required. Binary codes, however, are discrete and thus have no continuous derivatives. Relaxing the problem by solving it in a continuous space and then quantizing the solution is not guaranteed to yield separable binary codes. The quantization needs to be included in the optimization. In this paper we push for quantization: We optimize maximum class separability in the binary space. We introduce a margin on distances between dissimilar image pairs as measured in the binary space. In addition to pair-wise distances, we draw inspiration from Fisher's Linear Discriminant Analysis (Fisher LDA) to maximize the binary distances between classes and at the

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2019push

Related papers

• Deep Hashing Via Householder Quantization (2023)0.00
• One Loss For Quantization: Deep Hashing With Discrete Wasserstein Distributional Matching (2022)12.40
• HHF: Hashing-guided Hinge Function For Deep Hashing Retrieval (2021)14.24
• Deep Supervised Discrete Hashing (2017)0.00
• Simultaneous Compression And Quantization: A Joint Approach For Efficient Unsupervised Hashing (2018)7.50
• Deep Asymmetric Hashing With Dual Semantic Regression And Class Structure Quantization (2021)6.77
• PHPQ: Pyramid Hybrid Pooling Quantization For Efficient Fine-grained Image Retrieval (2021)8.60
• Deep Class-wise Hashing: Semantics-preserving Hashing Via Class-wise Loss (2018)11.19