Learning Invariant Representations with Local Transformations

06/27/2012
by   Kihyuk Sohn, et al.
0

Learning invariant representations is an important problem in machine learning and pattern recognition. In this paper, we present a novel framework of transformation-invariant feature learning by incorporating linear transformations into the feature learning algorithms. For example, we present the transformation-invariant restricted Boltzmann machine that compactly represents data by its weights and their transformations, which achieves invariance of the feature representation via probabilistic max pooling. In addition, we show that our transformation-invariant feature learning framework can also be extended to other unsupervised learning methods, such as autoencoders or sparse coding. We evaluate our method on several image classification benchmark datasets, such as MNIST variations, CIFAR-10, and STL-10, and show competitive or superior classification performance when compared to the state-of-the-art. Furthermore, our method achieves state-of-the-art performance on phone classification tasks with the TIMIT dataset, which demonstrates wide applicability of our proposed algorithms to other domains.

READ FULL TEXT

page 5

page 6

research
03/01/2017

Graph-based Isometry Invariant Representation Learning

Learning transformation invariant representations of visual data is an i...
research
08/21/2018

Isometric Transformation Invariant Graph-based Deep Neural Network

Learning transformation invariant representations of visual data is an i...
research
06/18/2012

On multi-view feature learning

Sparse coding is a common approach to learning local features for object...
research
03/20/2023

EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning

Learning to predict agent motions with relationship reasoning is importa...
research
05/31/2017

Controllable Invariance through Adversarial Feature Learning

Learning meaningful representations that maintain the content necessary ...
research
06/28/2016

Theta-RBM: Unfactored Gated Restricted Boltzmann Machine for Rotation-Invariant Representations

Learning invariant representations is a critical task in computer vision...
research
02/04/2015

Learning Local Invariant Mahalanobis Distances

For many tasks and data types, there are natural transformations to whic...

Please sign up or login with your details

Forgot password? Click here to reset