Sparse Instance Activation for Real-Time Instance Segmentation

In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers. In contrast, we prop...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 4423 - 4432
Hauptverfasser: Cheng, Tianheng, Wang, Xinggang, Chen, Shaoyu, Zhang, Wenqiang, Zhang, Qian, Huang, Chang, Zhang, Zhaoxiang, Liu, Wenyu
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.01.2022
Schlagworte:
Aggregates
Benchmark testing
categorization
Computer vision
Convolutional codes
grouping and shape analysis; Recognition: detection
Object detection
Pattern recognition
Real-time systems
retrieval
Segmentation
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers. In contrast, we propose a sparse set of instance activation maps, as a new object representation, to high-light informative regions for each foreground object. Then instance-level features are obtained by aggregating features according to the highlighted regions for recognition and segmentation. Moreover, based on bipartite matching, the instance activation maps can predict objects in a one-to-one style, thus avoiding non-maximum suppression (NMS) in post-processing. Owing to the simple yet effective designs with instance activation maps, SparseInst has extremely fast inference speed and achieves 40 FPS and 37.9 AP on the COCO benchmark, which significantly out-performs the counterparts in terms of speed and accuracy. Code and models are available at https://github.com/hustvl/SparseInst.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.00439