Active Image Indexing

TL;DR

This paper introduces active image indexing, which enhances image copy detection by making imperceptible modifications to images to improve retrieval accuracy in large databases.

Contribution

It proposes a novel method that optimizes the interaction between neural image representations and similarity search algorithms through imperceptible image adjustments.

Findings

40% improvement in Recall@1 on various transformations

Enhanced robustness of image retrieval systems

Effective integration with existing indexing structures

Abstract

Image copy detection and retrieval from large databases leverage two components. First, a neural network maps an image to a vector representation, that is relatively robust to various transformations of the image. Second, an efficient but approximate similarity search algorithm trades scalability (size and speed) against quality of the search, thereby introducing a source of error. This paper improves the robustness of image copy detection with active indexing, that optimizes the interplay of these two components. We reduce the quantization loss of a given image representation by making imperceptible changes to the image before its release. The loss is back-propagated through the deep neural network back to the image, under perceptual constraints. These modifications make the image more retrievable. Our experiments show that the retrieval and copy detection of activated images is significantly improved. For instance, activation improves by $+40\%$ the Recall1@1 on various image transformations, and for several popular indexing structures based on product quantization and locality sensitivity hashing.