Integrating Local Material Recognition with Large-Scale Perceptual Attribute Discovery

TL;DR

This paper presents a neural network architecture that automatically discovers perceptual material attributes during local material category recognition, leveraging a large-scale database and auxiliary loss to improve recognition and interpretability.

Contribution

It introduces a novel MAC-CNN that learns perceptual attributes within a recognition framework, linking attribute discovery with category recognition in a unified model.

Findings

Discovered attributes align with meaningful material traits.

Enabled recognition of unseen material categories with few examples.

Showed attributes can be learned jointly with recognition in an end-to-end network.

Abstract

Material attributes have been shown to provide a discriminative intermediate representation for recognizing materials, especially for the challenging task of recognition from local material appearance (i.e., regardless of object and scene context). In the past, however, material attributes have been recognized separately preceding category recognition. In contrast, neuroscience studies on material perception and computer vision research on object and place recognition have shown that attributes are produced as a by-product during the category recognition process. Does the same hold true for material attribute and category recognition? In this paper, we introduce a novel material category recognition network architecture to show that perceptual attributes can, in fact, be automatically discovered inside a local material recognition framework. The novel material-attribute-category convolutional neural network (MAC-CNN) produces perceptual material attributes from the intermediate pooling layers of an end-to-end trained category recognition network using an auxiliary loss function that encodes human material perception. To train this model, we introduce a novel large-scale database of local material appearance organized under a canonical material category taxonomy and careful image patch extraction that avoids unwanted object and scene context. We show that the discovered attributes correspond well with semantically-meaningful visual material traits via Boolean algebra, and enable recognition of previously unseen material categories given only a few examples. These results have strong implications in how perceptually meaningful attributes can be learned in other recognition tasks.