Learning to Detect A Salient Object Reporter: 鄭綱 (3/2)
Outline Introduction CRF Formulation of Static Salient Object Strong Contrast Center-Surround Histogram Color Spatial-Distribution Learning & Inference for the Model Formulation of Dynamic Salient Object Results Conclusion References
Introduction Image Labeling Problem Sky Building Lawn Plane Tree
Introduction Which kinds of information can be used for labeling? Features from individual sites Intensity, color, texture, … Interactions with neighboring sites Contextual information Vegetation Sky or Building?
Introduction Contextual information: 2 types of interactions Interaction with neighboring labels (Spatial smoothness of labels) neighboring sites tend to have similar labels(except at the discontinuities) Interactions with neighboring observed data Building Sky
Introduction Let be the label of the node of the image set S, and N i be the neighboring nodes of node i. Three kinds of information for image labeling Features from local node Interaction with neighboring labels Interaction with neighboring observed data node iS-{i}NiNi
Introduction General formulation: where and are called association potential and interaction potential.
Introduction Labels in Spatial Data are NOT independent! – spatially adjacent labels are often the same (Markov Random Fields and Conditional Random Fields) – spatially adjacent elements that have similar features often receive the same label (Conditional Random Fields) – spatially adjacent elements that have different features may not have correlated labels (Conditional Random Fields)
Salient Object? Salience Map?
Formulation of Static Salient Object Detection CRF model (static image): Salient object featurePairwise feature Strong contrast Center- surround histogram Color spatial- distribution Maximize!! Minimize!!
Strong Contrast Generate contrast map for each level of 6- level Gaussian pyramid. Then do linear combination. Input imageLevel 1 Level 4
Center-Surround Histogram Salient object usually has a “huge” difference from local area. ……. More different between 2 rectangles !
Center-Surround Histogram where …... ??
Color Spatial-Distribution The wider a color is distributed in the image, the less possible a salient object contains this color. Each pixel is assigned to a color component with the probability:
Color Spatial-Distribution Then the feature can be defined as a weighted sum:
Formulation of Static Salient Object Detection CRF model (static image): Salient object featurePairwise feature Strong contrast Center- surround histogram Color spatial- distribution Maximize!! Minimize!!
Learning & Inference for the Model The goal of CRF learning is to estimate the linear weights. Gradient descent Training images
Learning & Inference for the Model A training image for example: where An training image Label inferred this iterate Possible label Label per pixel
Learning & Inference for the Model Gradient descent: How to use ground-truth information? Where is the labeled ground-truth. t: iteration
Learning & Inference for the Model Situations: Ground-truth mistake!!!
Ground-Truth Mistake Solution: apply Gaussian function to weight every pixel in the rectangle.
Inference We should find the most probable labeling to maximize in training & detection. BP – Max-product Belief Propagation [Pearl ‘86] + Can be applied to any energy function – In vision results are usually worse than that of graph cuts – Does not always converge TRW - Max-product Tree-reweighted Message Passing [Wainwright, Jaakkola, Willsky ‘02], [Kolmogorov ‘05] + Can be applied to any energy function + Convergence guarantees for the algorithm in [Kolmogorov ’05]
Formulation of Dynamic Salient Object Detection Similar as static salient object detection! Static Salient feature Maximize!! Contrast of motion Center- surround histogram Spatial- distribution of motion Penalty term of motion
Results From left to right: input image, multi-scale contrast, center- surround histogram, color spatial distribution, and binary mask by CRF.
Results From left to right: Fuzzy growing based method Salience map Their approach Ground-truth
Results 1. multi-scale contrast 2. center-surround histogram 3. color spatial distribution 4. combination all Image set AImage set B 1. FG 2. SM 3. their approach
Conclusion They model the salient object detection by CRF, where a group of salient features are combined through CRF learning. It’s a set of novel local, regional & global salient features to define a generic salient object. Multi-object & no object cases are left as future work.
References (paper & book) “Learning to Detect A Salient Object”, CVPR 2007, PAMI “A Model of Saliency-Based Visual Attention for Rapid Scene Analysis”, PAMI, “Pattern Recognition and Machine Learning”, C. M. Bishop.
References (about CRF) “Discriminative Random Fields”, IJCV, i= &rep=rep1&type=pdf i= &rep=rep1&type=pdf “Conditional Random Fields: An Introduction”, H. M. Wallach. i= &rep=rep1&type=pdf i= &rep=rep1&type=pdf “Log-linear models & conditional random fields”, C. Elkan, l.pdf l.pdf
References (about TRW) “MAP estimation via agreement on (hyper) trees: Message-passing and linear programming approaches”, IEEE transaction on Information Theory, “Convergent Tree-Reweighted Message Passing for Energy Minimization”, PAMI, &rep=rep1&type=pdf &rep=rep1&type=pdf “A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors”, PAMI, &rep=rep1&type=pdf &rep=rep1&type=pdf