CS 766 Assignment 3: Locality-constrained Linear Coding for Scene Classification

Saikat R. Gomes (saikat@cs.wisc.edu) & Stephen Lazzaro (slazzaro@cs.wisc.edu)

Contents

  1. Introduction
  2. Hard Code Word
    1. Results
  3. Locality-constrained Linear
    1. Results
  4. Grid Search
  5. Sequential Hierarchy Classifier
    1. Manually assigned clusters
      1. Results
    2. Clusters from K-means
      1. Results
  6. Other Dataset Evaluation
    1. Birds
    2. Butterflies
  7. Other Experiments
    1. Results
  8. Scene Datasets
  9. Code
  10. Git Logs
  11. References

K-Means Assigned Clusters

In the first level, instead of supervising and denoting 2 broad groups, we used K-means (k=2) to separate the scenes into 2 groups.
The images were first classified as one of these groups and passed down the pipeline like the manual version.