ForestHash: Semantic Hashing with Shallow Random Forests and Tiny Convolutional Networks

Published

Journal Article

© 2018, Springer Nature Switzerland AG. In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests. A binary hash code for a data point is obtained by a set of decision trees, setting ‘1’ for the visited tree leaf, and ‘0’ for the rest. We propose to first randomly group arriving classes at each tree split node into two groups, obtaining a significantly simplified two-class classification problem that can be a handled with a light-weight CNN weak learner. Code uniqueness is achieved via the random class grouping, whilst code consistency is achieved using a low-rank loss in the CNN weak learners that encourages intra-class compactness for the two random class groups. Finally, we introduce an information-theoretic approach for aggregating codes of individual trees into a single hash code, producing a near-optimal unique hash for each class. The proposed approach significantly outperforms state-of-the-art hashing methods for image retrieval tasks on large-scale public datasets, and is comparable to image classification methods while utilizing a more compact, efficient and scalable representation. This work proposes a principled and robust procedure to train and deploy in parallel an ensemble of light-weight CNNs, instead of simply going deeper.

Full Text

Duke Authors

Cited Authors

  • Qiu, Q; Lezama, J; Bronstein, A; Sapiro, G

Published Date

  • January 1, 2018

Published In

Volume / Issue

  • 11206 LNCS /

Start / End Page

  • 442 - 459

Electronic International Standard Serial Number (EISSN)

  • 1611-3349

International Standard Serial Number (ISSN)

  • 0302-9743

Digital Object Identifier (DOI)

  • 10.1007/978-3-030-01216-8_27

Citation Source

  • Scopus