Home > Research > Publications & Outputs > On Trivial Solution and High Correlation Proble...

Associated organisational unit

Electronic data

  • 2018-3

    Accepted author manuscript, 2.3 MB, PDF document

Links

View graph of relations

On Trivial Solution and High Correlation Problems in Deep Supervised Hashing

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published
Close
Publication date1/02/2018
Host publication32nd AAAI Conference on Artificial Intelligence 2018
Place of PublicationPalo Alto
PublisherAAAI
Pages2240-2247
Number of pages8
ISBN (print)9781577358008
<mark>Original language</mark>English

Abstract

Deep supervised hashing (DSH), which combines binary learning and convolutional neural network, has attracted considerable research interests and achieved promising performance for highly efficient image retrieval. In this paper, we show that the widely used loss functions, pair-wise loss and triplet loss, suffer from the trivial solution problem and usually lead to highly correlated bits in practice, limiting the performance of DSH. One important reason is that it is difficult to incorporate proper constraints into the loss functions under the mini-batch based optimization algorithm. To tackle these problems, we propose to adopt ensemble learning strategy for deep model training. We found out that this simple strategy is capable of effectively decorrelating different bits, making the hashcodes more informative. Moreover, it is very easy to parallelize the training and support incremental model learning, which are very useful for real-world applications but usually ignored by existing DSH approaches. Experiments on benchmarks demonstrate the proposed ensemble based DSH can improve the performance of DSH approaches significant.