Bayesian semantic instance segmentation in open set world

Trung Pham, B. G. Vijay Kumar, Thanh-Toan Do, Gustavo Carneiro, Ian Reid

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

6 Citations (Scopus)

Abstract

This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation methods requires annotation masks for all object instances, which is expensive to acquire or even infeasible in some realistic scenarios, where the number of categories may increase boundlessly. In this paper, we present a novel open-set semantic instance segmentation approach capable of segmenting all known and unknown object classes in images, based on the output of an object detector trained on known object classes. We formulate the problem using a Bayesian framework, where the posterior distribution is approximated with a simulated annealing optimization equipped with an efficient image partition sampler. We show empirically that our method is competitive with state-of-the-art supervised methods on known classes, but also performs well on unknown classes when compared with unsupervised methods.

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2018
Subtitle of host publication15th European Conference Munich, Germany, September 8–14, 2018 Proceedings, Part X
EditorsVittorio Ferrari, Martial Hebert, Cristian Sminchisescu, Yair Weiss
Place of PublicationCham Switzerland
PublisherSpringer
Pages3-18
Number of pages16
ISBN (Electronic)9783030012496
ISBN (Print)9783030012489
DOIs
Publication statusPublished - 2018
Externally publishedYes
EventEuropean Conference on Computer Vision 2018 - Munich, Germany
Duration: 8 Sep 201814 Sep 2018
Conference number: 15th
https://eccv2018.org/
https://link.springer.com/book/10.1007/978-3-030-01246-5 (Proceedings)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11214
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceEuropean Conference on Computer Vision 2018
Abbreviated titleECCV 2018
CountryGermany
CityMunich
Period8/09/1814/09/18
Internet address

Keywords

  • Instance segmentation
  • Open-set conditions

Cite this