Download presentation

Presentation is loading. Please wait.

Published byJason Scandrett Modified over 4 years ago

1
Semantic Contours from Inverse Detectors Bharath Hariharan et.al. (ICCV-11)

2
Problem Localizing and classifying category-specific object contours in real world images Class specific contours Low-level contours (No-class specific)

3
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

4
- 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 G ij – scores the likelihood of a pixel (i,j) lying on a contour R 1,..., R l – l activation windows of the detector s k – score corresponding to each activation window R k Inverse detector

5
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 R K, assigned into one of bins (from SO) Feature Vector at a location (i, j), and detector R K: index of the bin into which the pixel (i, j) falls e n : 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

6
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

7
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)

8
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:

9
Semantic Boundaries Dataset (SBD) 8498 training images and 2820 test images (both instance specific and class specific)

10
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

11
Experiments 8498 training images and 2820 test images Baseline comparison with the low level contour generated by contour detector[1] Improve both MF and AP by a factor of 5 wrt to the bottom up contour detector Single stage contour detector that combines the outputs of all inverse detectors across all categories does better than two stage detector. Best performance: transportation means (aeroplane, bicycle, bus, car, motorbike, train), people, bottles, TV monitors Worst: chairs, dining tables, potted plants, boats and birds (hard to detect) [1] - Contour detection and hierarchical image segmentation. P. Arbelaez et.al, PAMI-2011

12
Experiments

13
Thank you

Similar presentations

OK

Hierarchical Dirichlet Process (HDP) A Dirichlet process (DP) is a discrete distribution that is composed of a weighted sum of impulse functions. Weights.

Hierarchical Dirichlet Process (HDP) A Dirichlet process (DP) is a discrete distribution that is composed of a weighted sum of impulse functions. Weights.

© 2018 SlidePlayer.com Inc.

All rights reserved.

To make this website work, we log user data and share it with processors. To use this website, you must agree to our Privacy Policy, including cookie policy.

Ads by Google