Hierarchical Material Recognition from Local Appearance
This work addresses material recognition for vision applications, but it is incremental as it builds on existing methods with a new taxonomy and dataset.
The paper tackles hierarchical material recognition from local appearance by introducing a taxonomy and dataset, and presents a graph attention network method that achieves state-of-the-art performance, with demonstrated generalization to adverse conditions and few-shot learning capabilities.
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.