Transfer Learning for Material Classification using Convolutional Networks
This work addresses material classification for computer vision applications, but it is incremental as it applies an existing transfer learning method to a specific domain.
The paper tackles material classification in natural settings by using a Convolutional Neural Network with transfer learning from object recognition, achieving significantly higher recognition rates compared to previous state-of-the-art approaches, and introduces a new dataset of approximately 10k images across 10 material categories.
Material classification in natural settings is a challenge due to complex interplay of geometry, reflectance properties, and illumination. Previous work on material classification relies strongly on hand-engineered features of visual samples. In this work we use a Convolutional Neural Network (convnet) that learns descriptive features for the specific task of material recognition. Specifically, transfer learning from the task of object recognition is exploited to more effectively train good features for material classification. The approach of transfer learning using convnets yields significantly higher recognition rates when compared to previous state-of-the-art approaches. We then analyze the relative contribution of reflectance and shading information by a decomposition of the image into its intrinsic components. The use of convnets for material classification was hindered by the strong demand for sufficient and diverse training data, even with transfer learning approaches. Therefore, we present a new data set containing approximately 10k images divided into 10 material categories.