Unsupervised Semantic-Preserving Adversarial Hashing for Image Search

By Cheng Deng, Erkun Yang, Tongliang Liu, Jie Li, Dacheng Tao. 2019

150 citations recorded by the source corpus.

Hashing plays a pivotal role in nearest-neighbor searching for large-scale image retrieval. Recently, deep learning-based hashing methods have achieved promising performance. However, most of these deep methods involve discriminative models, which require large-scale, labeled training datasets, thus hindering their real-world applications. In this paper, we propose a novel strategy to exploit the semantic similarity of the training data and design an efficient generative adversarial framework to learn binary hash codes in an unsupervised manner. Specifically, our model consists of three different neural networks: an encoder network to learn hash codes from images, a generative network to generate images from hash codes, and a discriminative network to distinguish between pairs of hash codes and images. By adversarially training these networks, we successfully learn mutually coherent encoder and generative networks, and can output efficient hash codes from the encoder network. We also propose a novel strategy, which utilizes both feature and neighbor similarities, to construct a semantic similarity matrix, then use this matrix to guide the hash code learning process. Integrating the supervision of this semantic similarity matrix into the adversarial learning framework can efficiently preserve the semantic information of training data in Hamming space. The experimental results on three widely used benchmarks show that our method not only significantly outperforms several state-of-the-art unsupervised hashing methods, but also achieves comparable performance with popular supervised hashing methods.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Cheng Deng
3. Shiv Ram Dubey
4. Tao A. Xiang
5. Yi Yang
6. Tongliang Liu
7. Yi-Zhe Song
8. Chen Qian

Citations in the corpus

• GreedyNAS: Towards Fast One-Shot NAS With Greedy Supernet (2020, background): “By dint of automatic feature engineering, deep neural networks (DNNs) have achieved remarkable success in various computer vision tasks, such as image classification [37, 36, 41, 33, 32, 15, 39], visual generation [34, 35], image retrieval [40, 7, 8, 12] and semantic comprehension [18, 17].”
• Deep Spectral Clustering Using Dual Autoencoder Network (2019, methodology): “As an important task in unsupervised learning [43, 8, 22, 24] and vision communities [48], clustering [14] has been widely used in image segmentation [37], image categorization [45, 47], and digital media analysis [1].”
• Saliency Detection via a Multiple Self-Weighted Graph-Based Manifold Ranking (2020, methodology): “The problem of saliency detection have been addressed using a completely data-driven approach by training a deep convolutional neural network [27], [28].”
• Two-Stream Deep Hashing With Class-Specific Centers for Supervised Image Search (2020, background): “Representative ANN-search solutions can be divided into tree-based [29], [30] and hash-based methods [17], [31]–[35].”
• The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (2020, background): “More recent research has therefore concentrated on realizing parts in an unsupervised fashion [7], [9], [23], [32], [36], [43], [49].”
• A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, background): “[109], [110], [111] are also investigated for image retrieval.”