Regularized Discriminant Embedding for Visual Descriptor Learning
This work addresses robustness in visual descriptor learning for computer vision applications, but it appears incremental as it builds on existing metric learning and discriminant analysis methods.
The paper tackles the problem of learning robust image descriptors that remain discriminative under varying environmental conditions by focusing on challenging training pairs, resulting in improved distinction between relevant and look-alike images.
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.