Semantic Contours from Inverse detectors

Semantic Contours from Inverse detectors

Outline

• Introduction• Inverse detector• Localizing semantic contours• Experiments • Conclusion

Problem

• Localizing and classifying category-specific object contours in real world images

Class specific contours

Low-level contours(No-class specific)

[ J.Malik ,IEEE Trans. on PAMI 2011 ]

Naive Solution

• Localizing and classifying category-specific object contours in real world images

• Using detector outputs will result is contours from surrounding context

• To avoid this problem they propose the inverse detector

Outline

• Introduction• Inverse detector• Localizing semantic contours• Experiments • Conclusion

• - Feature vector for pixel (i, j)

The Inverse Detector

• Given localized contours I and object detector , the Inverse Detector produces the object contour image

• I – image• G – output of contour detector• Gij – scores the likelihood of a pixel (i,j) lying on a contour• R1, ..., Rl – l activation windows of the detector • sk – score corresponding to each activation window Rk

Inverse detector

Feature Vector• Each detector window divided into S spatial bins• Contours are binned into O orientation bins• For a pixel (i, j), for an activation window RK, assigned into one of bins (from SO)

• Feature Vector at a location (i, j), and detector RK:

• index of the bin into which the pixel (i, j) falls

• en: an SO-dimensional vector with 1 in the nth position and 0 otherwise

• Feature vector for pixel (i, j):• weighted sum of across all the activation windows

Inverse detectors

• Inverse detectors is of the following form:

• Complete system: use of inverse detectors for localizing semantic contours• Using poselet types object detectors[1]• bottom-up contour detector[2]

• where, learn weight vector using a linear SVM with these features

Inverse detector

[1]-Detecting people using mutually consistent poselet activation. L. Bourdev et.al., ECCV-2010[2] - Contour detection and hierarchical image segmentation. P. Arbelaez et.al, PAMI-2011

Outline

• Introduction• Inverse detector• Localizing semantic contours• Experiments • Conclusion

Localizing semantic contours using inverse detectors

• System has two stages • train inverse detectors for each poselet types

• let P poselets corresponding to category C be• combine output of these inverse detectors to produce category-specific contours

• Stage 1: train inverse detectors (of the following form) for each poselet (as discussed previously)

• Stage 2: combining the outputs of each of these inverse detectors

• Features: concatenate the outputs of the inverse detectors corresponding to each of the poselet type

• Train a linear SVM (with classifying each pixel belonging to object contour or not)

Combining information across categories

• Previous model: considers each category independently. • In this model: combine information from across categories• Propose two methods

Method 1 • First level: Train contour detector for each category separately• Second level: Train on the outputs of these contour detectors

• Feature vector at the second level:

Method 2

• Only One level: Train on the features which are the outputs of the inverse detectors corresponding to the poselets of all categories

• Feature vector this level:

Outline

• Introduction• Inverse detector• Localizing semantic contours• Experiments • Conclusion

Experiments

Semantic Boundaries Dataset (SBD)

• PASCAL VOC2011, 20categories , 2223images • 8498 training images and 2820 test images

Benchmark• Show precision-recall curve for a detector producing soft output, parameterized by the detection score• Report two summary statistics: • Average precision (AP)• maximal F-measure (MF) = (F = 2PR/(P+R)

• Precision: fraction of true contours among detections • Recall: fraction of ground-truth contours detected

precision and recall are practically zero

Experiments

Outline

• Introduction• Inverse detector• Localizing semantic contours• Experiments • Conclusion

Conclusion

• Three distinct contributions– A new task– A new annotated dataset– A semantic contour detector

Thank you