Latest Object Memory Management for Temporally Consistent Video Instance Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Seunghun, Seo, Jiwan, Choi, Minwoo, Han, Kiljoon, Jeong, Jaehoon, Durante, Zane, Adeli, Ehsan, Park, Sang Hyun, Im, Sunghoon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915410792677376
author Lee, Seunghun
Seo, Jiwan
Choi, Minwoo
Han, Kiljoon
Jeong, Jaehoon
Durante, Zane
Adeli, Ehsan
Park, Sang Hyun
Im, Sunghoon
author_facet Lee, Seunghun
Seo, Jiwan
Choi, Minwoo
Han, Kiljoon
Jeong, Jaehoon
Durante, Zane
Adeli, Ehsan
Park, Sang Hyun
Im, Sunghoon
contents In this paper, we present Latest Object Memory Management (LOMM) for temporally consistent video instance segmentation that significantly improves long-term instance tracking. At the core of our method is Latest Object Memory (LOM), which robustly tracks and continuously updates the latest states of objects by explicitly modeling their presence in each frame. This enables consistent tracking and accurate identity management across frames, enhancing both performance and reliability through the VIS process. Moreover, we introduce Decoupled Object Association (DOA), a strategy that separately handles newly appearing and already existing objects. By leveraging our memory system, DOA accurately assigns object indices, improving matching accuracy and ensuring stable identity consistency, even in dynamic scenes where objects frequently appear and disappear. Extensive experiments and ablation studies demonstrate the superiority of our method over traditional approaches, setting a new benchmark in VIS. Notably, our LOMM achieves state-of-the-art AP score of 54.0 on YouTube-VIS 2022, a dataset known for its challenging long videos. Project page: https://seung-hun-lee.github.io/projects/LOMM/
format Preprint
id arxiv_https___arxiv_org_abs_2507_19754
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Latest Object Memory Management for Temporally Consistent Video Instance Segmentation
Lee, Seunghun
Seo, Jiwan
Choi, Minwoo
Han, Kiljoon
Jeong, Jaehoon
Durante, Zane
Adeli, Ehsan
Park, Sang Hyun
Im, Sunghoon
Computer Vision and Pattern Recognition
In this paper, we present Latest Object Memory Management (LOMM) for temporally consistent video instance segmentation that significantly improves long-term instance tracking. At the core of our method is Latest Object Memory (LOM), which robustly tracks and continuously updates the latest states of objects by explicitly modeling their presence in each frame. This enables consistent tracking and accurate identity management across frames, enhancing both performance and reliability through the VIS process. Moreover, we introduce Decoupled Object Association (DOA), a strategy that separately handles newly appearing and already existing objects. By leveraging our memory system, DOA accurately assigns object indices, improving matching accuracy and ensuring stable identity consistency, even in dynamic scenes where objects frequently appear and disappear. Extensive experiments and ablation studies demonstrate the superiority of our method over traditional approaches, setting a new benchmark in VIS. Notably, our LOMM achieves state-of-the-art AP score of 54.0 on YouTube-VIS 2022, a dataset known for its challenging long videos. Project page: https://seung-hun-lee.github.io/projects/LOMM/
title Latest Object Memory Management for Temporally Consistent Video Instance Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.19754