Learning Multi-scale Representations for Material Classification

  title={Learning Multi-scale Representations for Material Classification},
  author={Wenbin Li},
  • Wenbin Li
  • Published in GCPR 2014
  • Computer Science
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… Expand
7 Citations
Leveraging Knowledge-based Inference for Material Classification
  • 7
Probing the Intra-Component Correlations within Fisher Vector for Material Classification
  • PDF
When VLAD Met Hilbert
  • 1
  • Highly Influenced
  • PDF
Statistical Learning over Manifolds and its applications in Computer Vision
  • PDF


Exploring features in a Bayesian framework for material recognition
  • 206
  • PDF
Toward Robust Material Recognition for Everyday Objects
  • 80
  • PDF
Recognizing Materials from Virtual Examples
  • 60
  • PDF
Large-Scale Feature Learning With Spike-and-Slab Sparse Coding
  • 89
  • PDF
A Statistical Approach to Material Classification Using Image Patch Exemplars
  • 590
  • PDF
Class-Specific Material Categorisation
  • 288
Self-taught learning: transfer learning from unlabeled data
  • 1,470
  • PDF
Kernel Descriptors for Visual Recognition
  • 342
  • PDF
Scene parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers
  • 196
  • PDF
Visual Recognition Using Local Quantized Patterns
  • 112
  • PDF