Binary Generative Adversarial Networks for Image Retrieval

By Jingkuan Song. 2017

205 citations recorded by the source corpus.

The most striking successes in image retrieval using deep hashing have mostly involved discriminative models, which require labels. In this paper, we use binary generative adversarial networks (BGAN) to embed images to binary codes in an unsupervised way. By restricting the input noise variable of generative adversarial networks (GAN) to be binary and conditioned on the features of each input image, BGAN can simultaneously learn a binary representation per image, and generate an image plausibly similar to the original one. In the proposed framework, we address two main problems: 1) how to directly generate binary codes without relaxation? 2) how to equip the binary representation with the ability of accurate image retrieval? We resolve these problems by proposing new sign-activation strategy and a loss function steering the learning process, which consists of new models for adversarial loss, a content loss, and a neighborhood structure loss. Experimental results on standard datasets (CIFAR-10, NUSWIDE, and Flickr) demonstrate that our BGAN significantly outperforms existing hashing methods by up to 107% in terms of mAP (See Table 2).

Subfields: Computer Vision and Pattern Recognition, Generative Models

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

In Generative Models

Citations in the corpus

Regionwise Generative Adversarial Image Inpainting for Large Missing Areas (2019, background): “Generative models [28], [29] are widely used in many areas for its strong ability of modeling and learning approximately true dataset distributions, including image generation [30]–[32], representation learning [33], image retrieval [34], [35], object detection [36], video applications [37], [38] an”
Artificial intelligence in the creative industries: a review (2020, methodology): “Analysis Ads/film analysis [65] [65] [65] GP [66] Content retrieval [67–70] [71] [72] PM [73] Fake detection [74,75] [74] Blockchain [76] Recommendation [77] Deep belief net [78] Contrast enhancement [79] [80] Histogram [81].”
Unsupervised Semantic-Preserving Adversarial Hashing for Image Search (2019, methodology): “learned hash codes for the proposed method and two deep baseline methods, Deepbit [47] and BGAN [61], on the CIFAR10 dataset with 64 hash bit length.”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, methodology): “GANs have been used for feature learning such as feature selection [277], hashing [278]–[285], and metric learning [286].”
A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, methodology): “Different types of networks are used to learn the binary description such as deep neural networks [87], convolutional neural networks [56], autoencoder networks [64], [152], siamese networks [156], triplet networks [112], generative adversarial networks [110], [171], [175], and deep variational netw”
Perceptual Pyramid Adversarial Networks for Text-to-Image Synthesis (2019, methodology): “Recently, GANs have been applied to various applications, especially in simulating complicated data distributions, like images (Song et al. 2018a; 2018b), music, texts (Gupta et al. 2018) and video (Li et al. 2018).”
Progressive Generative Hashing for Image Retrieval (2018, methodology): “Besides, it should be noted that the performance of ITQ is quite close to the deep hashing methods including DH, Deepbit and BGAN.”