Hierarchical Material Recognition from Local Appearance

TL;DR

This paper presents a hierarchical approach to material recognition using a new taxonomy, a diverse dataset, and graph attention networks, achieving state-of-the-art results and demonstrating robustness and rapid learning in real-world conditions.

Contribution

It introduces a novel taxonomy and dataset for hierarchical material recognition and develops a graph attention network-based method that outperforms existing approaches.

Findings

Achieved state-of-the-art performance in material recognition.

Demonstrated robustness to adverse real-world imaging conditions.

Showed rapid learning of new materials with few-shot learning.

Abstract

We introduce a taxonomy of materials for hierarchical recognition from local appearance. Our taxonomy is motivated by vision applications and is arranged according to the physical traits of materials. We contribute a diverse, in-the-wild dataset with images and depth maps of the taxonomy classes. Utilizing the taxonomy and dataset, we present a method for hierarchical material recognition based on graph attention networks. Our model leverages the taxonomic proximity between classes and achieves state-of-the-art performance. We demonstrate the model's potential to generalize to adverse, real-world imaging conditions, and that novel views rendered using the depth maps can enhance this capability. Finally, we show the model's capacity to rapidly learn new materials in a few-shot learning setting.