Files in this item



application/pdfSUN-THESIS-2021.pdf (59MB)Restricted to U of Illinois
(no description provided)PDF


Title:Amodal video instance segmentation
Author(s):Sun, Mingxi
Advisor(s):Schwing, Alexander
Department / Program:Computer Science
Discipline:Computer Science
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):machine learning
computer vision
instance segmentation
amodal segmentation
Abstract:We explore approaches to improve over existing amodal prediction models for the task of semantic amodal instance level video object segmentation, i.e., the task to delineate objects and their occluded parts in video data. We propose Amodal-Net with three improvements: First, we leverage temporal information. Specifically, we employ 3D convolutions and a flow alignment module which permits to aggregate the objects’ features across frames. Second, we develop a cascaded box-head with soft-non-maximum-suppression to address the challenge that amodal segmentations overlap significantly. Third, we address the challenge that occlusions require observation information to be propagated over larger distances by developing an attention-based mask-head. Then we also study reprojection, another way of using temporal information which also uses 3D information. We evaluate our approach on amodal segmentation for video data, SAILVOS.
Issue Date:2021-07-23
Rights Information:Copyright 2021 Mingxi Sun
Date Available in IDEALS:2022-01-12
Date Deposited:2021-08

This item appears in the following Collection(s)

Item Statistics