CaltechAUTHORS
  A Caltech Library Service

MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training

Huang, De-An and Yu, Zhiding and Anandkumar, Anima (2022) MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20221221-004633960

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20221221-004633960

Abstract

We propose MinVIS, a minimal video instance segmentation (VIS) framework that achieves state-of-the-art VIS performance with neither video-based architectures nor training procedures. By only training a query-based image instance segmentation model, MinVIS outperforms the previous best result on the challenging Occluded VIS dataset by over 10% AP. Since MinVIS treats frames in training videos as independent images, we can drastically sub-sample the annotated frames in training videos without any modifications. With only 1% of labeled frames, MinVIS outperforms or is comparable to fully-supervised state-of-the-art approaches on YouTube-VIS 2019/2021. Our key observation is that queries trained to be discriminative between intra-frame object instances are temporally consistent and can be used to track instances without any manually designed heuristics. MinVIS thus has the following inference pipeline: we first apply the trained query-based image instance segmentation to video frames independently. The segmented instances are then tracked by bipartite matching of the corresponding queries. This inference is done in an online fashion and does not need to process the whole video at once. MinVIS thus has the practical advantages of reducing both the labeling costs and the memory requirements, while not sacrificing the VIS performance. Code is available at: https://github.com/NVlabs/MinVIS


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/2208.02245arXivDiscussion Paper
ORCID:
AuthorORCID
Huang, De-An0000-0002-6945-7768
Anandkumar, Anima0000-0002-6974-6797
Record Number:CaltechAUTHORS:20221221-004633960
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20221221-004633960
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:118536
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:22 Dec 2022 18:49
Last Modified:22 Dec 2022 18:49

Repository Staff Only: item control page