Learning Invariant Representations with Local Transformations

TL;DR

This paper introduces a new framework for learning invariant features by integrating linear transformations into existing algorithms, improving robustness and performance across various image and audio classification tasks.

Contribution

The paper proposes a transformation-invariant feature learning framework applicable to multiple unsupervised methods, including RBMs, autoencoders, and sparse coding, demonstrating broad applicability.

Findings

Achieves state-of-the-art results on TIMIT phone classification.

Shows competitive performance on image classification benchmarks.

Extends invariant learning to various unsupervised models.

Abstract

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.