Deep convolutional filter banks for texture recognition and segmentation

TL;DR

This paper introduces D-CNN, a new texture descriptor based on Fisher Vector pooling of CNN filter banks, significantly improving texture and scene recognition accuracy, and effectively localizing stuff categories in cluttered scenes.

Contribution

The paper presents D-CNN, a novel texture descriptor that enhances recognition accuracy and domain transferability without requiring feature adaptation or fully-connected layers.

Findings

Achieves 82.3% accuracy on Flickr material dataset

Attains 81.1% accuracy on MIT indoor scenes

Sets new state-of-the-art in texture and scene recognition

Abstract

Research in texture recognition often concentrates on the problem of material recognition in uncluttered conditions, an assumption rarely met by applications. In this work we conduct a first study of material and describable texture at- tributes recognition in clutter, using a new dataset derived from the OpenSurface texture repository. Motivated by the challenge posed by this problem, we propose a new texture descriptor, D-CNN, obtained by Fisher Vector pooling of a Convolutional Neural Network (CNN) filter bank. D-CNN substantially improves the state-of-the-art in texture, mate- rial and scene recognition. Our approach achieves 82.3% accuracy on Flickr material dataset and 81.1% accuracy on MIT indoor scenes, providing absolute gains of more than 10% over existing approaches. D-CNN easily trans- fers across domains without requiring feature adaptation as for methods that build on the fully-connected layers of CNNs. Furthermore, D-CNN can seamlessly incorporate multi-scale information and describe regions of arbitrary shapes and sizes. Our approach is particularly suited at lo- calizing stuff categories and obtains state-of-the-art re- sults on MSRC segmentation dataset, as well as promising results on recognizing materials and surface attributes in clutter on the OpenSurfaces dataset.