Max-Margin Invariant Features from Transformed Unlabeled Data
This work addresses the unlabeled transformation problem in semi-supervised and one-shot learning, offering a solution with theoretical guarantees for applications like face recognition.
The paper tackles the problem of learning invariant features when transformed labeled data is unavailable, proposing Max-Margin Invariant Features (MMIF) to address this unlabeled transformation problem. It demonstrates efficacy on large-scale datasets, including 153,000 images and a new LFW protocol, outperforming strong baselines.
The study of representations invariant to common transformations of the data is important to learning. Most techniques have focused on local approximate invariance implemented within expensive optimization frameworks lacking explicit theoretical guarantees. In this paper, we study kernels that are invariant to a unitary group while having theoretical guarantees in addressing the important practical issue of unavailability of transformed versions of labelled data. A problem we call the Unlabeled Transformation Problem which is a special form of semi-supervised learning and one-shot learning. We present a theoretically motivated alternate approach to the invariant kernel SVM based on which we propose Max-Margin Invariant Features (MMIF) to solve this problem. As an illustration, we design an framework for face recognition and demonstrate the efficacy of our approach on a large scale semi-synthetic dataset with 153,000 images and a new challenging protocol on Labelled Faces in the Wild (LFW) while out-performing strong baselines.