Hashing in the zero shot framework with domain adaptation

Abstract

Techniques to learn hash codes which can store and retrieve large dimensional multimedia data efficiently have attracted broad research interests in the recent years. With rapid explosion of newly emerged concepts and online data, existing supervised hashing algorithms suffer from the problem of scarcity of ground truth annotations due to the high cost of obtaining manual annotations. Therefore, we propose an algorithm to learn a hash function from training images belonging to 'seen' classes which can efficiently encode images of 'unseen' classes to binary codes. Specifically, we project the image features from visual space and semantic features from semantic space into a common Hamming subspace. Earlier works to generate hash codes have tried to relax the discrete constraints on hash codes and solve the continuous optimization problem. However, it often leads to quantization errors. In this work, we use the max-margin classifier to learn an efficient hash function. To address the concern of domain-shift which may arise due to the introduction of new classes, we also introduce an unsupervised domain adaptation model in the proposed hashing framework. Results on the three datasets show the advantage of using domain adaptation in learning a high-quality hash function and superiority of our method for the task of image retrieval performance as compared to several state-of-the-art hashing methods.

Deep visual domain adaptation: A survey

“…Over the past decades, various shallow DA methods have been proposed to solve a domain shift between the source and target domains. The common algorithms for shallow DA can mainly be categorized into two classes: instance-based DA [6], [18] and feature-based DA [37], [82], [30], [81]. The first class reduces the discrepancy by reweighting the source samples, and it trains on the weighted source samples.…”

Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining

“…AwA dataset contains 50 animals species. For fair comparison, we following the setting of the most similar work domain adaptation zero-shot hashing (DA-ZSH) [23], which also uses the unlabeled data of the novel classes. Specially, 10 classes are selected as the target classes and the rest 40 classes as the seen classes.…”

“…Guo et al [28] proposed transductive zero-shot recognition via jointly learning the shared model space for transferring the knowledge between the classes. The most similar work is [23], which formulated it as the domain adaptation problem for zeroshot hashing. Given the features of a mini-batch of images belong to the unseen classes, it updates the transformation matrix learned from the seen classes in each iteration.…”

“…For all deep learning-based methods, the weights of layers are initialized by the pre-trained AlexNet model 4 unless noted otherwise. IMH [27], COSDISH [8], SDH [26], ZSH [35], One-Stage Hashing [12] and Domain Adaptation Zero-shot Hashing (DA-ZSH) [23] are selected as the baselines.…”

“…However, due to source classes and target classes have different data distributions, using the hash functions learned from the source dataset without any adaptation to the target dataset may causes an unknown bias, which is called projection domain shift problem [1,24]. Pachori et al [23] introduced an unsupervised domain-adaptation model for ZSH, which updated the learned hash model by the query data from the target classes.…”