Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval

Page view(s)
35
Checked on Jan 18, 2025
Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval
Title:
Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval
Journal Title:
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval (ICMR)
Publication Date:
06 June 2017
Citation:
O. Morere, L. Jie, A. Veillard, L.Duan, V. Chandrasekhar, T. Poggio, "Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval", Proceedings of ACM International Conference on Multimedia Retrieval (ICMR)
Abstract:
The goal of this work is the computation of very compact binary hashes for image instance retrieval. Our approach has two novel contributions. The first one is Nested Invariance Pooling (NIP), a method inspired from i-theory, a mathematical theory for computing group invariant transformations with feed-forward neural networks. NIP is able to produce compact and well-performing descriptors with visual representations extracted from convolutional neural networks. We specifically incorporate scale, translation and rotation invariances but the scheme can be extended to any arbitrary sets of transformations. We also show that using moments of increasing order throughout nesting is important. The NIP descriptors are then hashed to the target code size (32-256 bits) with a Restricted Boltzmann Machine with a novel batch-level regularization scheme specifically designed for the purpose of hashing (RBMH). A thorough empirical evaluation with state-of-the-art shows that the results obtained both with the NIP descriptors and the NIP+RBMH hashes are consistently outstanding across a wide range of datasets.
License type:
PublisherCopyrights
Funding Info:
Description:
© ACM 2017. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in http://dx.doi.org/10.1145/3078971.3078987
ISBN:
978-1-4503-4701-3
Files uploaded:

File Size Format Action
sample-nip.pdf 3.14 MB PDF Open