Invariant Feature Coding using Tensor Product Representation
Abstract: In this study, a novel feature coding method that exploits invariance for transformations represented by a finite group of orthogonal matrices is proposed. We prove that the group-invariant feature vector contains sufficient discriminative information when learning a linear classifier using convex loss minimization. Based on this result, a novel feature model that explicitly considers group action is proposed for principal component analysis and k-means clustering, which are commonly used in most feature coding methods, and global feature functions. Although the global feature functions are in general complex nonlinear functions, the group action on this space can be easily calculated by constructing these functions as tensor-product representations of basic representations, resulting in an explicit form of invariant feature functions. The effectiveness of our method is demonstrated on several image datasets.
Submission Length: Long submission (more than 12 pages of main content)
Changes Since Last Submission: Add the discussion about computational complexity.
Assigned Action Editor: ~Seungjin_Choi1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 897
Loading