Particular object retrieval with integral max-pooling of CNN activations

TL;DR

This paper introduces an integral max-pooling method for CNN activations that enables efficient object localization and improves image retrieval performance, competing with traditional methods on standard benchmarks.

Contribution

It proposes a novel integral max-pooling technique for CNN features that enhances object localization and retrieval accuracy without multiple network inputs.

Findings

Achieved state-of-the-art results on Oxford5k and Paris6k datasets.

Enabled geometry-aware re-ranking using CNN-based features.

Improved retrieval performance over existing CNN-based methods.

Abstract

Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not compatible with geometry-aware re-ranking methods and still outperformed, on some particular object retrieval benchmarks, by traditional image search systems relying on precise descriptor matching, geometric re-ranking, or query expansion. This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information derived from the CNN. We build compact feature vectors that encode several image regions without the need to feed multiple inputs to the network. Furthermore, we extend integral images to handle max-pooling on convolutional layer activations, allowing us to efficiently localize matching objects. The resulting bounding box is finally used for image re-ranking. As a result, this paper significantly improves existing CNN-based recognition pipeline: We report for the first time results competing with traditional methods on the challenging Oxford5k and Paris6k datasets.