Push for Quantization: Deep Fisher Hashing

08/31/2019
by   Yunqiang Li, et al.
0

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 same time minimize the binary distance of images within the same class. Experiments on CIFAR-10, NUS-WIDE and ImageNet100 demonstrate compact codes comparing favorably to the current state of the art.

READ FULL TEXT
research
03/29/2019

Asymmetric Deep Semantic Quantization for Image Retrieval

Due to its fast retrieval and storage efficiency capabilities, hashing h...
research
06/07/2019

Deep Spherical Quantization for Image Search

Hashing methods, which encode high-dimensional images with compact discr...
research
03/12/2018

Deep Class-Wise Hashing: Semantics-Preserving Hashing via Class-wise Loss

Deep supervised hashing has emerged as an influential solution to large-...
research
02/21/2018

Binary Constrained Deep Hashing Network for Image Retrieval without Human Intervention

Learning compact binary codes for image retrieval problem using deep neu...
research
12/04/2021

HHF: Hashing-guided Hinge Function for Deep Hashing Retrieval

Deep hashing has shown promising performance in large-scale image retrie...
research
01/14/2022

ViT2Hash: Unsupervised Information-Preserving Hashing

Unsupervised image hashing, which maps images into binary codes without ...
research
10/08/2018

Deep LDA Hashing

The conventional supervised hashing methods based on classification do n...

Please sign up or login with your details

Forgot password? Click here to reset