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
  • [21] ISOODLV2 SEMANTIC INSTANCE SEGMENTATION OF TOUCHING AND OVERLAPPING OBJECTS
    Boehm, Anion
    Tatachenko, Maxim
    Falk, Thorsten
    2019 IEEE 16TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2019), 2019, : 343 - 347
  • [22] Dynamic Object Detection Revolution: Deep Learning with Attention, Semantic Understanding, and Instance Segmentation for Real-World Precision
    Shai, Karimunnisa
    Banerjee, Dyuti
    Begum, R. Sabin
    Srikanth, Narne
    Narasimharao, Jonnadula
    El-Ebiary, Yousef A. Baker
    Thenmozhi, E.
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (01) : 443 - 454
  • [23] Variational Bayesian Level Set for Image Segmentation
    Qu, Han-Bing
    Xiang, Lin
    Wang, Jia-Qiang
    Li, Bin
    Tao, Hai-Jun
    SIXTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2013), 2013, 9067
  • [24] Detection of Knots in Oak Wood Planks: Instance versus Semantic segmentation
    Urtans, Evalds
    Bumanis, Karlis
    Vecins, Valters
    Ancans, Maris
    Andrijanova, Aiga
    Upenieks, Marcis Teodors
    Volkovs, Kristofers
    2022 IEEE THE 5TH INTERNATIONAL CONFERENCE ON BIG DATA AND ARTIFICIAL INTELLIGENCE (BDAI 2022), 2022, : 163 - 168
  • [25] Open World Entity Segmentation
    Qi, Lu
    Kuen, Jason
    Wang, Yi
    Gu, Jiuxiang
    Zhao, Hengshuang
    Torr, Philip
    Lin, Zhe
    Jia, Jiaya
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (07) : 8743 - 8756
  • [26] The Detection Method of Potato Foliage Diseases in Complex Background Based on Instance Segmentation and Semantic Segmentation
    Li, Xudong
    Zhou, Yuhong
    Liu, Jingyan
    Wang, Linbai
    Zhang, Jun
    Fan, Xiaofei
    FRONTIERS IN PLANT SCIENCE, 2022, 13
  • [27] Instance Segmentation Algorithm Based on Semantic Alignment and Graph Node Interaction
    Zhang Min
    Deng Yangyang
    Li Yajun
    Zhang Miaohui
    LASER & OPTOELECTRONICS PROGRESS, 2023, 60 (22)
  • [28] Joint Semantic-Instance Segmentation Method for Intelligent Transportation System
    Li, Yujie
    Cai, Jintong
    Zhou, Quan
    Lu, Huimin
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2023, 24 (12) : 15540 - 15547
  • [29] Bayesian deep learning for semantic segmentation of food images
    Aguilar, Eduardo
    Nagarajan, Bhalaji
    Remeseiro, Beatriz
    Radeva, Petia
    COMPUTERS & ELECTRICAL ENGINEERING, 2022, 103
  • [30] Semantic segmentation based on neural network and Bayesian network
    Ge, Wenying
    Liu, Guoying
    MIPPR 2013: MULTISPECTRAL IMAGE ACQUISITION, PROCESSING, AND ANALYSIS, 2013, 8917