Presentation is loading. Please wait.

Presentation is loading. Please wait.

Unsupervised Detection of Regions of Interest Using Iterative Link Analysis Gunhee Kim 1 Antonio Torralba 2 1: SCS, CMU 2: CSAIL, MIT Neural Information.

Similar presentations


Presentation on theme: "Unsupervised Detection of Regions of Interest Using Iterative Link Analysis Gunhee Kim 1 Antonio Torralba 2 1: SCS, CMU 2: CSAIL, MIT Neural Information."— Presentation transcript:

1 Unsupervised Detection of Regions of Interest Using Iterative Link Analysis Gunhee Kim 1 Antonio Torralba 2 1: SCS, CMU 2: CSAIL, MIT Neural Information Processing Systems 2009 November 30, 2009

2 Unsupervised Detection of ROIs A set of images… Rectangular Regions of Interest

3 Why Is the ROI Detection Useful ? Scene recognition [Quattoni&Torralba, CVPR09] Training for Recognition [Bosch et al, ICCV07] Flickr Notes

4 Alternating Optimization One of widely used heuristics for iterative optimization Optimization over two sets of variables is not easy But affordable to optimize one while the other is fixed

5 Goal: Find correspondences between two sets of point clouds [Besl&McKay,1992] Example – Iterative Closest Point Algorithm Trans- formation Estimate transformation parameters Corres- pondences Associate points by NN criteria

6 Goal: Clustering Example – K-means Cluster Membership Find nearest cluster center Cluster Centers Take mean Initialization Pictures from Bishop’s book

7 Goal: Find best ROIs in each image of dataset Unsupervised Detection of ROIs Refine ROIs Detection or Localization Find Examplars Modeling or Ranking examplars Where is butterfly? What are examplars?

8 Our Approach Inspired by alternating optimization Based on link analysis of hypothesis network. Find Examplars = Central and diverse Hubs Refine ROIs = Highly-ranked Hypotheses in each image wrt examplars Easy, Fast and Dynamic –Simple heuristic for linearity of computation wrt dataset size. –Ex. 4.5 hours / 200k images with naïve matlab implementation.

9 ROI Candidates and Description For each, define –At least one of would be good Description: Spatial pyramids of visual words and HOG Similarity measure: Cosine similarity An image15 segments43 ROI hypotheses Visual wordsEdge Gradient

10 Algorithm - Input Image set and its ROI hypothesis set

11 Algorithm - Initialization Best ROI = Image itself !

12 Algorithm - Initialization Initialization is essential for the success ! Why is it a feasible idea for Web images ? –Most pictures are taken from a canonical view so that an object of interest is located in a center with significant size. –Given a similarity network of a sufficiently large number of images, democratic voting reveals the most dominant visual information as hubs [Kim et al 08] Examples of top-ranked Images

13 Algorithm – First Hub Seeking Generate a similarity network and find a hub set

14 Algorithm – First ROI Refinement Bipartite graph between hub sets and All ROIs of an image

15 Algorithm – Second Hub Seeking Keep iterating…

16 Hub Seeking with Centrality & Diversity Mean-shift like hub seeking algorithm Mean Shift [Comaniciu and Meer, PAMI 2002] K-NN similarity matrixPageRank vector G (t) K-NN graph Degree distribution ~ PageRank vector

17 Hub Seeking with Centrality & Diversity Mean-shift like hub seeking algorithm Max P-value ! Fixed radius window = max. reachable probability d (= 0.1) Mean Shift

18 ROI Refinement Augmented Bipartite Graph (1-α)W o WoTWoT αW i ROI hypothesisHub setvector ROI hypotheses Hub set PageRank Argmax () i

19 ROI Refinement What does α do? (1-α)W o WoTWoT αW i α = 0α = 0.1 WoWo WoTWoT

20 Example - ROI Refinement T=0T=1T=2T=3T=4T=5T=6T=7 T=0 T=1 T=2 T=3 T=4 T=5T=6 T=7

21 Scalability Setting Bottleneck: Quadratic computation to generate a similarity matrix of selected ROIs If dataset size is too large, –Run the algorithm with N number of images ( N = 10,000) –Re-use x % of previous high-ranked images. Dataset N N N N

22 Experiments Performance Test –PASCAL VOC 2006 Dataset –Weakly-supervised 1 and Unsupervised 2 Scalability Test –Five objects: {butterfly+insect (69,990), classic+car (265,731), motorcycle+bike (106,590), sunflower (165,235), giraffe+zoo (53,620)} –Weakly-supervised 1 1: Input imageset consists of a single object type (only localization is required) 2: Input imageset consists of multiple object types (localization and clustering are required)

23 Performance Tests Weakly Supervised Localization (PR-Curves) [Russell et al. CVPR 2006] seg discovery/index.html X-axis: Recall Y-axis: Precision

24 Performance Tests Unsupervised Classification & Localization X-axis: Recall Y-axis: Precision X-axis: FP rate Y-axis: TP rate ROC Curves PR Curves

25 Scalability Tests Weakly-supervised Localization X-axis: Recall Y-axis: Precision

26 Perturbation Tests Robustness of ROI detection of each image against random network formation –100 random sets of size of 200 images Entropy: Dataset An image of interest X-axis: ROI hypotheses Y-axis: Frequencies

27 Localization Examples

28 Conclusion Alternating optimization based Unsupervised ROI detection Simple and Fast Competitive performance on PASCAL 06 Scalable Test with more than 200K Flickr images Critic: Analysis for convexity, convergence, sensitivity to initialization, quality of solution

29 Algorithm


Download ppt "Unsupervised Detection of Regions of Interest Using Iterative Link Analysis Gunhee Kim 1 Antonio Torralba 2 1: SCS, CMU 2: CSAIL, MIT Neural Information."

Similar presentations


Ads by Google