Learning Multi-Scale Representations for Material Classification

TL;DR

This paper introduces a multi-scale feature learning approach for material classification, demonstrating that learned features outperform traditional descriptors on standard benchmarks.

Contribution

It proposes two strategies to incorporate scale into feature learning, creating a novel multi-scale coding method for improved material recognition.

Findings

Learned features outperform hand-crafted descriptors on FMD and KTH-TIPS2 datasets.

Multi-scale coding enhances the effectiveness of feature learning for material recognition.

The approach advances unsupervised feature learning in the context of material classification.

Abstract

The recent progress in sparse coding and deep learning has made unsupervised feature learning methods a strong competitor to hand-crafted descriptors. In computer vision, success stories of learned features have been predominantly reported for object recognition tasks. In this paper, we investigate if and how feature learning can be used for material recognition. We propose two strategies to incorporate scale information into the learning procedure resulting in a novel multi-scale coding procedure. Our results show that our learned features for material recognition outperform hand-crafted descriptors on the FMD and the KTH-TIPS2 material classification benchmarks.