Semantic Segmentation using Regions and Parts
-
Upload
abra-weaver -
Category
Documents
-
view
48 -
download
0
description
Transcript of Semantic Segmentation using Regions and Parts
![Page 1: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/1.jpg)
SEMANTIC SEGMENTATION USING REGIONS AND PARTS
Pablo Arbel´aez1, Bharath Hariharan1, Chunhui Gu1,2, Saurabh Gupta1, Lubomir Bourdev1,3,† and Jitendra Malik1
1University of California, Berkeley - Berkeley, CA 947202Google Inc., 1600 Amphitheatre Pkwy, Mountain View, CA 940433Facebook, 1601 Willow Rd, Menlo Park, CA 94025
![Page 2: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/2.jpg)
OUTLINE
Introduction Related Work Region Generation Region Representation Region Scoring Pixel Classification Experiments
![Page 3: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/3.jpg)
INTRODUCTION
Bottom-up region cues and top-down part detectors provide complementary information for recognizing articulated objects.
![Page 4: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/4.jpg)
INTRODUCTION
![Page 5: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/5.jpg)
RELATED WORK
CRF Approaches Refining top-down detections Scoring bottom-up region
hypotheses
![Page 6: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/6.jpg)
REGION GENERATION
Uses bottom-up regions as object candidates
Generate object candidates building on the segmentation method of [4]
Compute UCMs at three resolutions of the input image
[4] P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik. Contour detection and hierarchical image segmentation. IEEE Trans. on PAMI, 2011.
![Page 7: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/7.jpg)
REGION REPRESENTATION
Part Compatibility Features Part Activations
use the poselet framework introduced in [8, 7] use pre-trained models and masks from [9]
Part-Based Region Ranking
|I | : the total area of the imageα = (α1, ..., α6) ∈ N6
[7] L. Bourdev, S. Maji, T. Brox, and J. Malik. Detecting people using mutually consistent poselet activations. In Proc. ECCV, 2010.[8] L. Bourdev and J. Malik. Poselets: Body part detectors trained using 3d human pose annotations. In Proc. ICCV, 2009.[9] T. Brox, L. Bourdev, S. Maji, and J. Malik. Object segmentation by alignment of poselet activations to image contours. In Proc. CVPR, 2011
![Page 8: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/8.jpg)
REGION REPRESENTATION
Part Compatibility Features Part-Based Region Ranking
P = {P1, ..., PA}
![Page 9: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/9.jpg)
REGION REPRESENTATION
Global Appearance Features a set of first-order appearance cues defined
on the region support Shape, Color, Texture
Semantic Contours Features 4 region features per semantic contour map
Generic geometrical properties 16 generic geometric properties for each
region
![Page 10: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/10.jpg)
REGION REPRESENTATION
Multi-Class Features the three high-level descriptor types are
category-specific and the low-level geometric properties are shared
![Page 11: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/11.jpg)
REGION SCORING
Predict the probability of belonging to each category of interest for each object candidate
After classification, each region is assigned a score for all the categories of interest
![Page 12: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/12.jpg)
PIXEL CLASSIFICATION
Train a final set of classifiers that operate on pixels rather than on regions average maximum non-max suppression
![Page 13: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/13.jpg)
EXPERIMENTS
Control Experiments
Calibration of multiple detectors through pixel classification
![Page 14: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/14.jpg)
EXPERIMENTS
Test set performance
![Page 15: Semantic Segmentation using Regions and Parts](https://reader035.fdocuments.in/reader035/viewer/2022062304/56813321550346895d99f64c/html5/thumbnails/15.jpg)
EXPERIMENTS