Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval

Abstract

With the rapid growth of web images, hashing has received increasing interests in large scale image retrieval. Research efforts have been devoted to learning compact binary codes that preserve semantic similarity based on labels. However, most of these hashing methods are designed to handle simple binary similarity. The complex multilevel semantic structure of images associated with multiple labels have not yet been well explored. Here we propose a deep semantic ranking based method for learning hash functions that preserve multilevel semantic similarity between multi-label images. In our approach, deep convolutional neural network is incorporated into hash functions to jointly learn feature representations and mappings from them to hash codes, which avoids the limitation of semantic representation power of hand-crafted features. Meanwhile, a ranking list that encodes the multilevel similarity information is employed to guide the learning of such deep hash functions. An effective scheme based on surrogate loss is used to solve the intractable optimization problem of nonsmooth and multivariate ranking measures involved in the learning procedure. Experimental results show the superiority of our proposed approach over several state-of-the-art hashing methods in term of ranking evaluation metrics when tested on multi-label image datasets.

CVPR 2015

References in corpus (4)

• One weird trick for parallelizing convolutional neural networks
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Deep Convolutional Ranking for Multilabel Image Annotation
• Optimizing Ranking Measures for Compact Binary Code Learning

Cited by in corpus (33)

• Person Re-identification: Past, Present and Future
• Deep Supervised Discrete Hashing
• A scikit-based Python environment for performing multi-label classification
• Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
• HashNet: Deep Learning to Hash by Continuation
• Deep Region Hashing for Efficient Large-scale Instance Search from Images
• How to Train Triplet Networks with 100K Identities?
• Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification
• Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing
• AMC: Attention guided Multi-modal Correlation Learning for Image Search
• A Revisit on Deep Hashings for Large-scale Content Based Image Retrieval
• Efficient end-to-end learning for quantizable representations
• Learning a Repression Network for Precise Vehicle Search
• Simultaneous Feature Aggregating and Hashing for Large-scale Image Search
• MIHash: Online Hashing with Mutual Information
• Asymmetric Deep Supervised Hashing
• End-to-End Supervised Product Quantization for Image Search and Retrieval
• Jointly Extracting Relations with Class Ties via Effective Deep Ranking
• Improving the Annotation of DeepFashion Images for Fine-grained Attribute Recognition
• Query-adaptive Image Retrieval by Deep Weighted Hashing
• Ranking-based Deep Cross-modal Hashing
• Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network
• Accurate Deep Representation Quantization with Gradient Snapping Layer for Similarity Search
• Deep Supervised Hashing with Triplet Labels
• Deep Momentum Uncertainty Hashing
• Rescuing Deep Hashing from Dead Bits Problem
• Regularizing Deep Hashing Networks Using GAN Generated Fake Images
• Improving Deep Binary Embedding Networks by Order-aware Reweighting of Triplets
• Shared Predictive Cross-Modal Deep Quantization
• Learning a Complete Image Indexing Pipeline
• NIST: An Image Classification Network to Image Semantic Retrieval
• Hashing with Binary Matrix Pursuit
• A Scalable Optimization Mechanism for Pairwise based Discrete Hashing