Regularized Discriminant Embedding for Visual Descriptor Learning

TL;DR

This paper introduces a regularized discriminant analysis method to learn robust image representations that are invariant to environmental changes, improving the discrimination between matching and non-matching image patches.

Contribution

It proposes a novel regularized discriminant embedding technique that emphasizes challenging pairs, enhancing the robustness of visual descriptors against environmental variations.

Findings

Better discrimination between relevant and irrelevant image patches.

Improved robustness of image representations to environmental changes.

Outperforms existing metric learning methods in distinguishing similar-looking patches.

Abstract

Images can vary according to changes in viewpoint, resolution, noise, and illumination. In this paper, we aim to learn representations for an image, which are robust to wide changes in such environmental conditions, using training pairs of matching and non-matching local image patches that are collected under various environmental conditions. We present a regularized discriminant analysis that emphasizes two challenging categories among the given training pairs: (1) matching, but far apart pairs and (2) non-matching, but close pairs in the original feature space (e.g., SIFT feature space). Compared to existing work on metric learning and discriminant analysis, our method can better distinguish relevant images from irrelevant, but look-alike images.