Zhuang, F., & Moulin, P. (2023). Label-Consistent Generalizable Hash Codes. IEEE Transactions on Information Forensics and Security, 18, 4075–4085. https://doi.org/10.1109/tifs.2023.3290790
Abstract:
We present a supervised semantic hashing framework, named Label-Consistent Generalized Hashing (LCGH). The main novelty of LCGH is the explicit retention of information which may be irrelevant in training, but possibly useful for generalizing to unseen test classes. This is in stark contrast to typical semantic hashing methods which seek to remove redundant feature information from their hash codes in order to maximize the margin between hash codes of dissimilar data. This typical strategy leaves hash codes narrowly viable for discerning between training classes, and inadequate in discriminating
between unseen test classes. Instead of limiting the information
content of hash codes to those provided by the training labels,
LCGH enhances its codes with information content from both
supervised and unsupervised sources, improving their ability to
discriminate across a wider range of data. To do so, LCGH
builds upon the foundation of first agreeing with the provided
training labels (label-consistency) and then incorporating possibly
useful information using a reconstruction loss. In this way, LCGH
respects the reliably given label information before exploring the
addition of possibly useful ones. The outcome is a hashing scheme
with slightly weaker within-domain (training and test classes are
the same) retrieval performance, but much stronger cross-domain
(training and test classes are disjoint) performance.
License type:
Publisher Copyright
Funding Info:
This work was supported in part by the National Science Foundation
under Grant CCF 12-19145 and CCF 15-27388 and in part by the American Universities International Programs Fellowship and the National Science Scholarship through Agency for Science, Technology and Research (A*STAR) Graduate Academy, Singapore.