Max-Margin Invariant Features from Transformed Unlabeled Data

10/24/2017
by   Dipan K. Pal, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/18/2015

Unitary-Group Invariant Kernels and Features from Transformed Unlabeled Data

The study of representations invariant to common transformations of the ...
research
11/22/2016

Max-Margin Deep Generative Models for (Semi-)Supervised Learning

Deep generative models (DGMs) are effective on learning multilayered rep...
research
07/15/2020

Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translation

Scarcity of labeled data has motivated the development of semi-supervise...
research
10/27/2021

Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose

We study the problem of learning to estimate the 3D object pose from a f...
research
04/23/2022

Transformation Invariant Cancerous Tissue Classification Using Spatially Transformed DenseNet

In this work, we introduce a spatially transformed DenseNet architecture...
research
05/26/2011

Efficient Learning of Sparse Invariant Representations

We propose a simple and efficient algorithm for learning sparse invarian...
research
10/27/2017

Not-So-Random Features

We propose a principled method for kernel learning, which relies on a Fo...

Please sign up or login with your details

Forgot password? Click here to reset