Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval

TitleNested Invariance Pooling and RBM Hashing for Image Instance Retrieval
Publication TypeJournal Article
Year of Publication2016
AuthorsMorère, O, Veillard, A, Chandrasekhar, V, Poggio, T
JournalarXiv.org
Date Published03/2016
KeywordsCNN, Hashing, Image Instance Retrieval, Invariant Representation, Regularization, unsupervised learning
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.

URLhttps://arxiv.org/abs/1603.04595
Download:  PDF icon 1603.04595.pdf

Research Area: 

CBMM Relationship: 

  • CBMM Related