Learning Multi-scale Representations for Material Classification

The recent progress in sparse coding and deep learning has made unsupervised feature learning methods a strong competitor to hand-crafted descriptors. In computer vision, success stories of learned features have been predominantly reported for object recognition tasks. In this paper, we investigate if and how feature learning can be used for material recognition. We propose two strategies to incorporate scale information into the learning procedure resulting in a novel multi-scale coding procedure. Our results show that our learned features for material recognition outperform hand-crafted descriptors on the FMD and the KTH-TIPS2 material classification benchmarks.

• Publication year

  2014

• Venue

  German Conference on Pattern Recognition

• Publication date

  2014-08-13

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1007/978-3-319-11752-2_65arXiv 1408.2938
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Pairwise Rotation Invariant Co-Occurrence Local Binary Pattern

  2014cited by this paper
• Large-Scale Feature Learning With Spike-and-Slab Sparse Coding

  2012influential reference
• Scene parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers

  2012cited by this paper
• Recognizing Materials from Virtual Examples

  2012cited by this paper
• Visual Recognition Using Local Quantized Patterns

  2012influential reference
• LIBSVM: A library for support vector machines

  2011cited by this paper
• A Spike and Slab Restricted Boltzmann Machine

  2011cited by this paper
• Unsupervised Models of Images by Spikeand-Slab RBMs

  2011cited by this paper
• Toward Robust Material Recognition for Everyday Objects

  2011cited by this paper
• Theano: A CPU and GPU Math Compiler in Python

  2010cited by this paper
• Kernel Descriptors for Visual Recognition

  2010cited by this paper
• Exploring features in a Bayesian framework for material recognition

  2010cited by this paper
• A Statistical Approach to Material Classification Using Image Patch Exemplars

  2009cited by this paper
• Self-taught learning: transfer learning from unlabeled data

  2007cited by this paper
• Greedy Layer-Wise Training of Deep Networks

  2006cited by this paper
• A Fast Learning Algorithm for Deep Belief Nets

  2006cited by this paper
• Class-specific material categorisation

  2005influential reference
• On the Significance of Real-World Conditions for Material Classification

  2004cited by this paper
• A Statistical Approach to Texture Classification from Single Images

  2004cited by this paper
• Multi-scale Binary Patterns for Texture Analysis

  2003cited by this paper
• Classifying Images of Materials: Achieving Viewpoint and Illumination Independence

  2002cited by this paper
• Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

  2002influential reference
• Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons

  2001cited by this paper
• Reflectance and texture of real-world surfaces

  1999cited by this paper
• A comparative study of texture measures with classification based on featured distributions

  1996cited by this paper
• Emergence of simple-cell receptive field properties by learning a sparse code for natural images

  1996cited by this paper
• Exploiting Tractable Substructures in Intractable Networks

  1995cited by this paper

• Boosting Texture-Based Classification by Describing Statistical Information of Gray-Levels Differences

  2019cites this paper
• Statistical Learning over Manifolds and its applications in Computer Vision

  2018cites this paper
• Material Recognition Meets 3D Reconstruction: Novel Tools for Efficient, Automatic Acquisition Systems

  2017cites this paper
• Local binary circumferential and radial derivative pattern for texture classification

  2017cites this paper
• Probing the Intra-Component Correlations within Fisher Vector for Material Classification

  2016cites this paper
• When VLAD Met Hilbert

  2015influential citation
• A Short Survey on Optical Material Recognition

  2015cites this paper
• Leveraging Knowledge-based Inference for Material Classification

  2015cites this paper