Multi-level Texture Encoding and Representation (MuLTER) based on Deep Neural Networks

TL;DR

This paper introduces MuLTER, a multi-level texture encoding network that combines features at different levels to improve recognition accuracy in texture classification tasks, with efficient architecture and state-of-the-art results.

Contribution

The paper presents MuLTER, a novel multi-level pooling architecture that effectively fuses low- and high-level features for enhanced texture recognition.

Findings

MuLTER outperforms existing texture descriptors on MINC-2500 and GTOS-mobile datasets.

Multi-level feature fusion significantly improves recognition accuracy.

The architecture maintains fixed feature dimensions across different image sizes.

Abstract

In this paper, we propose a multi-level texture encoding and representation network (MuLTER) for texture-related applications. Based on a multi-level pooling architecture, the MuLTER network simultaneously leverages low- and high-level features to maintain both texture details and spatial information. Such a pooling architecture involves few extra parameters and keeps feature dimensions fixed despite of the changes of image sizes. In comparison with state-of-the-art texture descriptors, the MuLTER network yields higher recognition accuracy on typical texture datasets such as MINC-2500 and GTOS-mobile with a discriminative and compact representation. In addition, we analyze the impact of combining features from different levels, which supports our claim that the fusion of multi-level features efficiently enhances recognition performance. Our source code will be published on GitHub (https://github.com/olivesgatech).