Transfer Adversarial Hashing for Hamming Space Retrieval
This addresses a domain gap issue in hashing-based image retrieval, offering a solution for scenarios with mismatched source and target domains, though it is incremental as it builds on existing deep hashing methods.
The paper tackles the problem of image retrieval when training and database domains differ, introducing Transfer Adversarial Hashing (TAH) to align distributions and learn concentrated hash codes, achieving state-of-the-art performance in Hamming space retrieval.
Hashing is widely applied to large-scale image retrieval due to the storage and retrieval efficiency. Existing work on deep hashing assumes that the database in the target domain is identically distributed with the training set in the source domain. This paper relaxes this assumption to a transfer retrieval setting, which allows the database and the training set to come from different but relevant domains. However, the transfer retrieval setting will introduce two technical difficulties: first, the hash model trained on the source domain cannot work well on the target domain due to the large distribution gap; second, the domain gap makes it difficult to concentrate the database points to be within a small Hamming ball. As a consequence, transfer retrieval performance within Hamming Radius 2 degrades significantly in existing hashing methods. This paper presents Transfer Adversarial Hashing (TAH), a new hybrid deep architecture that incorporates a pairwise $t$-distribution cross-entropy loss to learn concentrated hash codes and an adversarial network to align the data distributions between the source and target domains. TAH can generate compact transfer hash codes for efficient image retrieval on both source and target domains. Comprehensive experiments validate that TAH yields state of the art Hamming space retrieval performance on standard datasets.