Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers

Unsupervised semantic segmentation aims to discover groupings within and across images that capture object-and view-invariance of a category without external supervision. Grouping naturally has levels of granularity, creating ambiguity in unsupervised segmentation. Existing methods avoid this ambigu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 2561 - 2571
Hauptverfasser: Ke, Tsung-Wei, Hwang, Jyh-Jing, Guo, Yunhui, Wang, Xudong, Yu, Stella X.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2022
Schlagworte:
Benchmark testing
categorization
Computer vision
grouping and shape analysis; Recognition: detection
Image segmentation
Representation learning
retrieval; Representation learning; Scene analysis and understanding; Self-& semi-& meta- & unsupervised learning
Segmentation
Semantics
Transformers
Visualization
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Unsupervised semantic segmentation aims to discover groupings within and across images that capture object-and view-invariance of a category without external supervision. Grouping naturally has levels of granularity, creating ambiguity in unsupervised segmentation. Existing methods avoid this ambiguity and treat it as a factor outside modeling, whereas we embrace it and desire hierarchical grouping consistency for unsupervised segmentation. We approach unsupervised segmentation as a pixel-wise feature learning problem. Our idea is that a good representation shall reveal not just a particular level of grouping, but any level of grouping in a consistent and predictable manner. We enforce spatial consistency of grouping and bootstrap feature learning with co-segmentation among multiple views of the same image, and enforce semantic consistency across the grouping hierarchy with clustering transformers between coarse- and fine-grained features. We deliver the first data-driven unsupervised hierarchical semantic segmentation method called Hierarchical Segment Grouping (HSG). Capturing visual similarity and statistical co-occurrences, HSG also outperforms existing un-supervised segmentation methods by a large margin on five major object- and scene-centric benchmarks.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.00260