Deep Discrete Hashing with Self-supervised Pairwise Labels (2017-07-07T00:00:00.000000Z)

TL;DR

Experimental results on standard datasets demonstrate that the proposed novel unsupervised deep hashing method, named Deep Discrete Hashing (DDH), significantly outperforms existing hashing methods by large margin in terms of mAP for image retrieval and object recognition.

Abstract

Hashing methods have been widely used for applications of large-scale image retrieval and classification. Non-deep hashing methods using handcrafted features have been significantly outperformed by deep hashing methods due to their better feature representation and end-to-end learning framework. However, the most striking successes in deep hashing have mostly involved discriminative models, which require labels. In this paper, we propose a novel unsupervised deep hashing method, named Deep Discrete Hashing (DDH), for large-scale image retrieval and classification. In the proposed framework, we address two main problems: (1) how to directly learn discrete binary codes? (2) how to equip the binary representation with the ability of accurate image retrieval and classification in an unsupervised way? We resolve these problems by introducing an intermediate variable and a loss function steering the learning process, which is based on the neighborhood structure in the original space. Experimental results on standard datasets (CIFAR-10, NUS-WIDE, and Oxford-17) demonstrate that our DDH significantly outperforms existing hashing methods by large margin in terms of mAP for image retrieval and object recognition. Code is available at https://github.com/htconquer/ddh.

Authors

Lianli Gao

4 papers

Jingkuan Song

4 papers

Tao He

1 papers

TL;DR

Abstract

Authors

References49 items

Quantization-based hashing: a general framework for scalable image and video retrieval

Cross-heterogeneous-database age estimation through correlation representation learning

HashNet: Deep Learning to Hash by Continuation

SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning

Optimized Graph Learning Using Partial Tags and Multiple Features for Image and Video Annotation

Fast reference frame selection based on content similarity for low complexity HEVC encoder

Supervised Recurrent Hashing for Large Scale Video Retrieval

Joint Graph Learning and Video Segmentation via Multiple Cues and Topology Calibration

Learning to Hash with Binary Deep Neural Network

Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks

A Survey on Learning to Hash

Hash Learning with Convolutional Neural Networks for Semantic Based Image Retrieval

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

Resnet in Resnet: Generalizing Residual Architectures

Column Sampling Based Discrete Supervised Hashing

Deep Residual Learning for Image Recognition

Feature Learning Based Deep Supervised Hashing with Pairwise Labels

Online Learning to Rank for Content-Based Image Retrieval

Weakly Supervised RBM for Semantic Segmentation

Deep hashing for compact binary codes learning

Salient Object Detection via Augmented Hypotheses

Simultaneous feature learning and hash coding with deep neural networks

Going deeper with convolutions

ImageNet Large Scale Visual Recognition Challenge

Supervised hashing with latent factor models

Supervised Hashing for Image Retrieval via Image Representation Learning

Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval

Effective Multiple Feature Hashing for Large-Scale Near-Duplicate Video Retrieval

K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes

Learning Compact Binary Codes for Visual Tracking

Inter-media hashing for large-scale retrieval from heterogeneous data sources

Isotropic Hashing

ImageNet classification with deep convolutional neural networks

A new approach to interdomain routing based on secure multi-party computation

Spherical hashing

Semi-supervised hashing for scalable image retrieval

DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo

Learning to rank for content-based image retrieval

NUS-WIDE: a real-world web image database from National University of Singapore

Semantic hashing

Automated Flower Classification over a Large Number of Classes

Speeded-Up Robust Features (SURF)

Near-Optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions

A Visual Vocabulary for Flower Classification

Histograms of oriented gradients for human detection

Computer Vision and Image Understanding

Discriminative Learning of Local Image Descriptors

This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTION ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 Rotationally Invariant Descript

Learning Multiple Layers of Features from Tiny Images

Field of Study

Journal Information

Name

Volume