paper-with-me

홈 › Papers

TrickVOS: A Bag of Tricks for Video Object Segmentation

2023-06-27 · Evangelos Skartados, Konstantinos Georgiadis, Mehmet Kerim Yucel, Koskinas Ioannis, Armando Domi, Anastasios Drosou, Bruno Manganelli, Albert Saa-Garriga

Space-time memory (STM) network methods have been dominant in semi-supervised video object segmentation (SVOS) due to their remarkable performance. In this work, we identify three key aspects where we can improve such methods; i) supervisory signal, ii) pretraining and iii) spatial awareness. We then propose TrickVOS; a generic, method-agnostic bag of tricks addressing each aspect with i) a structure-aware hybrid loss, ii) a simple decoder pretraining regime and iii) a cheap tracker that imposes spatial constraints in model predictions. Finally, we propose a lightweight network and show that when trained with TrickVOS, it achieves competitive results to state-of-the-art methods on DAVIS and YouTube benchmarks, while being one of the first STM-based SVOS methods that can run in real-time on a mobile device.

📄 PDF Abstract BibTeX arXiv:2306.15377

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderObjectSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Similar Papers 제목 키워드 기반

The Second Place Solution for The 4th Large-scale Video Object Segmentation Challenge--Track 3: Referring Video Object Segmentation

2022-06-24 · Leilei Cao, Zhuang Li, Bo Yan, Feng Zhang 외

The referring video object segmentation task (RVOS) aims to segment object instances in a given video referred by a language expression in all video frames. Due to the requirement of understanding cross-modal semantics w…

Objectobject-detectionObject DetectionReferring Video Object Segmentation+5

1st Place Solution for YouTubeVOS Challenge 2021:Video Instance Segmentation

2021-06-12 · Thuy C. Nguyen, Tuan N. Tang, Nam LH. Phan, Chuong H. Nguyen 외

Video Instance Segmentation (VIS) is a multi-task problem performing detection, segmentation, and tracking simultaneously. Extended from image set applications, video data additionally induces the temporal information, w…

SegmentationVideo Instance Segmentation

Tracking Anything in High Quality

2023-07-26 · Jiawen Zhu, Zhenyu Chen, Zeqi Hao, Shijie Chang 외

Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject and box/mask-based tracking. Among them,…

ObjectObject TrackingSemantic SegmentationSemi-Supervised Video Object Segmentation+3

MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

2025-08-07 · Henghui Ding, Kaining Ying, Chang Liu, Shuting He 외 arxiv

Video object segmentation (VOS) aims to segment specified target objects throughout a video. Although state-of-the-art methods have achieved impressive performance (e.g., 90+% J&F) on benchmarks such as DAVIS and YouTube…

Video Object SegmentationVideo Object Tracking

2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020

2020-10-21 · Kai Jiang, Xiangyue Liu, Zheng Ju, Xiang Luo

Compared with MS-COCO, the dataset for the competition has a larger proportion of large objects which area is greater than 96x96 pixels. As getting fine boundaries is vitally important for large object segmentation, Mask…

Instance SegmentationObjectSegmentationSemantic Segmentation