Published on Wed Apr 04 2018

Discriminative Cross-View Binary Representation Learning

Liu Liu, Hairong Qi

Cross-view/cross-modal hashing for effective binary representation learning has received significant attention. Most existing cross-view hashingalgorithms emphasize the similarities in individual views. We propose an end-to-end method to learn semantic-preserving and discriminative binary representation.

0
0
0
Abstract

Learning compact representation is vital and challenging for large scale multimedia data. Cross-view/cross-modal hashing for effective binary representation learning has received significant attention with exponentially growing availability of multimedia content. Most existing cross-view hashing algorithms emphasize the similarities in individual views, which are then connected via cross-view similarities. In this work, we focus on the exploitation of the discriminative information from different views, and propose an end-to-end method to learn semantic-preserving and discriminative binary representation, dubbed Discriminative Cross-View Hashing (DCVH), in light of learning multitasking binary representation for various tasks including cross-view retrieval, image-to-image retrieval, and image annotation/tagging. The proposed DCVH has the following key components. First, it uses convolutional neural network (CNN) based nonlinear hashing functions and multilabel classification for both images and texts simultaneously. Such hashing functions achieve effective continuous relaxation during training without explicit quantization loss by using Direct Binary Embedding (DBE) layers. Second, we propose an effective view alignment via Hamming distance minimization, which is efficiently accomplished by bit-wise XOR operation. Extensive experiments on two image-text benchmark datasets demonstrate that DCVH outperforms state-of-the-art cross-view hashing algorithms as well as single-view image hashing algorithms. In addition, DCVH can provide competitive performance for image annotation/tagging.

Thu Aug 17 2017
Computer Vision
Deep Binary Reconstruction for Cross-modal Hashing
Cross-modal retrieval based on hashing technique has drawn much attention nowadays. It takes the binary codes of one modality as the query to retrieve the relevant hashing codes of another modality. We provide a Deep Binary Reconstruction (DBRC) network that can directly learn the hashing codes.
0
0
0
Sat Feb 01 2020
Machine Learning
Deep Multi-View Enhancement Hashing for Image Retrieval
Hashing is an efficient method for nearest neighbor search in large-scale data space by embedding high-dimensional feature descriptors into a similarity preserving Hamming space. Large-scale high-speed retrieval through binary code has a certain degree of reduction in retrieval Accuracy compared to traditional retrieval methods.
0
0
0
Mon Aug 13 2018
Machine Learning
Learning Discriminative Hashing Codes for Cross-Modal Retrieval based on Multi-view Features
Hashing techniques have been applied broadly in retrieval tasks due to their low storage requirements and high speed of processing. Many hashing methods have been extensively studied for information retrieval. A discrete hashing learning framework that jointly performs classifier learning and subspace learning is proposed.
0
0
0
Sat Aug 01 2020
Computer Vision
Unsupervised Deep Cross-modality Spectral Hashing
This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes. The framework is a two-step hashing approach which decouples the optimization into (1) binary optimization and (2
0
0
0
Tue Mar 26 2019
Computer Vision
Unsupervised Multi-modal Hashing for Cross-modal retrieval
Hashing learning has received much attention in the domain of Big Data. We propose a novel unsupervised hashing learning method to cope with this open problem. The experimental results show that our method can achieve superior performance over the state-of-the-art methods.
0
0
0
Sat Jan 05 2019
Computer Vision
Bilinear Supervised Hashing Based on 2D Image Features
Hashing has been recognized as an efficient representation learning method to handle big data. Most of the existing hashing methods focus on learning the low-dimensional vectorized binary features. This paper proposes a bilinear supervised discrete hashing (BSDH) method based on 2D image features.
0
0
0