Bayesian Semantic Instance Segmentation in Open Set World

被引:17
|
作者
Pham, Trung [1 ]
Kumar, B. G. Vijay [1 ]
Do, Thanh-Toan [1 ]
Carneiro, Gustavo [1 ]
Reid, Ian [1 ]
机构
[1] Univ Adelaide, Sch Comp Sci, Adelaide, SA, Australia
来源
COMPUTER VISION - ECCV 2018, PT X | 2018年 / 11214卷
基金
澳大利亚研究理事会;
关键词
Instance segmentation; Open-set conditions; IMAGE SEGMENTATION;
D O I
10.1007/978-3-030-01249-6_1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:3 / 18
页数:16
相关论文
共 50 条
  • [41] CODH plus plus : Macro-semantic differences oriented instance segmentation network
    Zhang, Wenchao
    Fu, Chong
    Cao, Lin
    Sham, Chiu-Wing
    EXPERT SYSTEMS WITH APPLICATIONS, 2022, 202
  • [42] Semantic Loopback Detection Method Based on Instance Segmentation and Visual SLAM in Autonomous Driving
    Huang, Li
    Zhu, Zhe
    Yun, Juntong
    Xu, Manman
    Liu, Ying
    Sun, Ying
    Hu, Jun
    Li, Fazeng
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 25 (03) : 3118 - 3127
  • [43] Object-Oriented 3D Semantic Mapping Based on Instance Segmentation
    Chi, Jinxin
    Wu, Hao
    Tian, Guohui
    JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2019, 23 (04) : 695 - 704
  • [44] Real-Time Instance-Aware Segmentation and Semantic Mapping on Edge Devices
    Lu, Junjie
    Tian, Bailing
    Shen, Hongming
    Zhang, Xuewei
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2023, 72
  • [45] Medical image segmentation based on the Bayesian level set method
    Chen, Yao-Tien
    Tseng, Din-Chang
    MEDICAL IMAGING AND INFORMATICS, 2008, 4987 : 25 - +
  • [46] Amodal Instance Segmentation
    Li, Ke
    Malik, Jitendra
    COMPUTER VISION - ECCV 2016, PT II, 2016, 9906 : 677 - 693
  • [47] Instance Segmentation with BoundaryNet
    Boyadzhiev, Teodor
    Ivanova, Krassimira
    COMBINATORIAL IMAGE ANALYSIS, IWCIA 2022, 2023, 13348 : 260 - 269
  • [48] Instance Segmentation in the Dark
    Linwei Chen
    Ying Fu
    Kaixuan Wei
    Dezhi Zheng
    Felix Heide
    International Journal of Computer Vision, 2023, 131 : 2198 - 2218
  • [49] Instance Segmentation in the Dark
    Chen, Linwei
    Fu, Ying
    Wei, Kaixuan
    Zheng, Dezhi
    Heide, Felix
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2023, 131 (08) : 2198 - 2218
  • [50] Recurrent Instance Segmentation
    Romera-Paredes, Bernardino
    Torr, Philip Hilaire Sean
    COMPUTER VISION - ECCV 2016, PT VI, 2016, 9910 : 312 - 329