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
  • [31] SEMANTIC AND INSTANCE-AWARE PIXEL-ADAPTIVE CONVOLUTION FOR PANOPTIC SEGMENTATION
    Song, Sumin
    Sagong, Min-Cheol
    Jung, Seung-Won
    Ko, Sung-Jea
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 16 - 20
  • [32] Open-Vocabulary Instance Segmentation-Boundary IS-Goal
    Tang, Quan
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2024, PT IV, 2025, 15034 : 420 - 435
  • [33] SOLO: A Simple Framework for Instance Segmentation
    Wang, Xinlong
    Zhang, Rufeng
    Shen, Chunhua
    Kong, Tao
    Li, Lei
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (11) : 8587 - 8601
  • [34] A Data-Centric Approach for Wind Plant Instance-Level Segmentation Using Semantic Segmentation and GIS
    de Carvalho, Osmar Luiz Ferreira
    de Carvalho Junior, Osmar Abilio
    de Albuquerque, Anesmar Olino
    Orlandi, Alex Gois
    Hirata, Issao
    Borges, Dibio Leandro
    Gomes, Roberto Arnaldo Trancoso
    Guimaraes, Renato Fontes
    REMOTE SENSING, 2023, 15 (05)
  • [35] DIFFUSIONINST: DIFFUSION MODEL FOR INSTANCE SEGMENTATION
    Gu, Zhangxuan
    Chen, Haoxing
    Xu, Zhuoer
    2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, ICASSP 2024, 2024, : 2730 - 2734
  • [36] Appearance quality classification method of Huangguan pear under complex background based on instance segmentation and semantic segmentation
    Zhang, Yuhang
    Shi, Nan
    Zhang, Hao
    Zhang, Jun
    Fan, Xiaofei
    Suo, Xuesong
    FRONTIERS IN PLANT SCIENCE, 2022, 13
  • [37] A Hybrid Level Set With Semantic Shape Constraint for Object Segmentation
    Wang, Bin
    Yuan, Xiuying
    Gao, Xinbo
    Li, Xuelong
    Tao, Dacheng
    IEEE TRANSACTIONS ON CYBERNETICS, 2019, 49 (05) : 1558 - 1569
  • [38] SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation
    Tao, An
    Duan, Yueqi
    Wei, Yi
    Lu, Jiwen
    Zhou, Jie
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 4952 - 4965
  • [39] COFI - Coarse-Semantic to Fine-Instance Unsupervised Mitochondria Segmentation in EM
    Aswath, Anusha
    Alsahaf, Ahmad
    Westenbrink, B. Daan
    Giepmans, Ben N. G.
    Azzopardi, George
    COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2023, PT II, 2023, 14185 : 87 - 97
  • [40] Box2Mask: Box-Supervised Instance Segmentation via Level-Set Evolution
    Li, Wentong
    Liu, Wenyu
    Zhu, Jianke
    Cui, Miaomiao
    Yu, Risheng
    Hua, Xiansheng
    Zhang, Lei
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (07) : 5157 - 5173