Hierarchical Sparse FRAME Models

Experiment 1: Learning a Mixture of Hierarchical Sparse FRAME Models for Clustering

clustering dataset

(1) code for mixture of hierarchical sparse FRAME models (2) code for mixture of And-Or templates (3) link to code for other methods

1. Experiment Setup

To evaluate the clustering quality, we introduce two metrics: conditional purity and conditional entropy. Given the underlying groundtruth category labels X (which is unknown to the algorithm) and the obtained cluster labels Y , the conditional purity is defined as the mean of the maximum category probabilities for (X, Y ),

and the conditional entropy is defined as,

where both p(y) and p(x|y) are estimated on the training set, and we would expect higher purity and lower entropy for a better clustering algorithm.

We compare clustering by hierarchical sparse FRAME model with (1) original sparse FRAME by matching pursuit [4], (2) sparse FRAME by generative boosting [5], (3) active basis model [1], (4) two-way EM [2], (5) k-mean with HOG features, and (6) And-Or Template [3].

The methods are evaluated in terms of conditional purity and conditional entropy. All the results are obtained based on 5 repetitions. It can be seen that our method performs significantly better than other methods.

2. Dataset

Profiles of UCLA mixture dataset for clustering tasks

	Description	# Clusters	Examples	# Images
Task 1	bull & cow	2		15/15
Task 2	cup & teapot	2		15/15
Task 3	plane & helicopter	2		15/15
Task 4	camel, elephant, & deer	3		15/15/15
Task 5	clocks (square, circle, triangle)	3		15/15/15
Task 6	seagull, swan, & eagle	3		15/15/15
Task 7	eye, nose, mouth, & ear	4		15/15/15/15
Task 8	flowers	4		15/15/15/15
Task 9	keyboard, mouse, monitor, & mainframe	4		15/15/15/15
Task 10	tiger, lion, cat, deer, & wolf	5		15/15/15/15/15
Task 11	musical intrument	5		15/15/15/15/15
Task 12	animal bodies	5		15/15/15/15/15

3. Evaluation

4. Comparison

5. Reference