What is Point Supervision Worth in Video Instance Segmentation?

Video instance segmentation (VIS) is a challenging vision task that aims to detect, segment, and track objects in videos. Conventional VIS methods rely on densely-annotated object masks which are expensive. We reduce the human annotations to only one point for each object in a video frame during tra...

Full description

Saved in:
Bibliographic Details
Main Authors: Huang, Shuaiyi, Huang, De-An, Yu, Zhiding, Lan, Shiyi, Radhakrishnan, Subhashree, Alvarez, Jose M., Shrivastava, Abhinav, Anandkumar, Anima
Format: Conference Proceeding
Language:English
Subjects:
Annotations
Computer vision
Instance segmentation
Object detection
Object segmentation
point supervision
Shape
Training
video instance segmentation
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Video instance segmentation (VIS) is a challenging vision task that aims to detect, segment, and track objects in videos. Conventional VIS methods rely on densely-annotated object masks which are expensive. We reduce the human annotations to only one point for each object in a video frame during training, and obtain high-quality mask predictions close to fully supervised models. Our proposed training method consists of a class-agnostic proposal generation module to provide rich negative samples and a spatio-temporal point-based matcher to match the object queries with the provided point annotations. Comprehensive experiments on three VIS benchmarks demonstrate competitive performance of the proposed framework, nearly matching fully supervised methods.
ISSN:2160-7516
DOI:10.1109/CVPRW63382.2024.00273