Paper Info
Title
Error Factor Analysis for Wild Scene Image-Labelling
Abstract
PASCAL VOC Segmentation Challenge [10] is currently considered as one of the datasets that reflect the image segmentation difficulties for real world scenarios [29]. However, current evaluation is simply based on a single Inter-section Over Union (IOU) score. In this paper, we try to discover the error factors under the IOU, which makes the results more informative to understand rather than a black box. Specifically, we decompose the error into three error types in terms of object characteristics, i.e. general, appearance and shape. Each error type is composed of respective factors, e.g. size and aspect ratio for general, appearance distinctiveness for appearance, etc. Finally, for each factor and error type, we perform analysis over its impact on and correlation with the final IOU through robust regression. Our experiments show that these error factors have significant relationship with the given IOU accuracy, and the analysis provides practical guidance on further improvement of the given algorithm.
Year
DOI
Venue
2015
10.1109/WACV.2015.109
WACV
Keywords
Field
DocType
iou score,regression analysis,pascal voc segmentation,error analysis,image segmentation,object characteristics,error factor analysis,image classification,wild scene image-labelling,robust regression,inter-section over union score,labeling,algorithm design and analysis,shape,accuracy,robustness,semantics
Black box (phreaking),Computer vision,Algorithm design,Scale-space segmentation,Pattern recognition,Computer science,Segmentation,Robustness (computer science),Image segmentation,Robust regression,Artificial intelligence,Optimal distinctiveness theory
Conference
ISSN
Citations 
PageRank 
2472-6737
0
0.34
References 
Authors
33
2
Name
Order
Citations
PageRank
Peng Wang125312.25
Alan L. Yuille2103391902.01