Object Recognition by Sequential Figure-Ground Ranking |
| |
Authors: | João Carreira Fuxin Li Cristian Sminchisescu |
| |
Affiliation: | (1) National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China;(2) College of Mathematics & Information Science, Wenzhou University, Wenzhou, 325000, Zhejiang, China;(3) Department of Computer Science and Information Systems, Birkbeck College, Malet Street, London, WC1E 7HX, UK;(4) State University of New York, Binghamton, NY 13902, USA |
| |
Abstract: | We present an approach to visual object-class segmentation and recognition based on a pipeline that combines multiple figure-ground
hypotheses with large object spatial support, generated by bottom-up computational processes that do not exploit knowledge
of specific categories, and sequential categorization based on continuous estimates of the spatial overlap between the image
segment hypotheses and each putative class. We differ from existing approaches not only in our seemingly unreasonable assumption
that good object-level segments can be obtained in a feed-forward fashion, but also in formulating recognition as a regression problem. Instead of focusing
on a one-vs.-all winning margin that may not preserve the ordering of segment qualities inside the non-maximum (non-winning)
set, our learning method produces a globally consistent ranking with close ties to segment quality, hence to the extent entire object or part hypotheses are likely to spatially
overlap the ground truth. We demonstrate results beyond the current state of the art for image classification, object detection
and semantic segmentation, in a number of challenging datasets including Caltech-101, ETHZ-Shape as well as PASCAL VOC 2009
and 2010. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|