paper-with-me

홈 › Papers

TIVE: A Toolbox for Identifying Video Instance Segmentation Errors

2022-10-17 · Wenhe Jia, Lu Yang, Zilong Jia, Wenyi Zhao, Yilin Zhou, Qing Song

Since first proposed, Video Instance Segmentation(VIS) task has attracted vast researchers' focus on architecture modeling to boost performance. Though great advances achieved in online and offline paradigms, there are still insufficient means to identify model errors and distinguish discrepancies between methods, as well approaches that correctly reflect models' performance in recognizing object instances of various temporal lengths remain barely available. More importantly, as the fundamental model abilities demanded by the task, spatial segmentation and temporal association are still understudied in both evaluation and interaction mechanisms. In this paper, we introduce TIVE, a Toolbox for Identifying Video instance segmentation Errors. By directly operating output prediction files, TIVE defines isolated error types and weights each type's damage to mAP, for the purpose of distinguishing model characters. By decomposing localization quality in spatial-temporal dimensions, model's potential drawbacks on spatial segmentation and temporal association can be revealed. TIVE can also report mAP over instance temporal length for real applications. We conduct extensive experiments by the toolbox to further illustrate how spatial segmentation and temporal association affect each other. We expect the analysis of TIVE can give the researchers more insights, guiding the community to promote more meaningful explorations for video instance segmentation. The proposed toolbox is available at https://github.com/wenhe-jia/TIVE.

📄 PDF Abstract BibTeX arXiv:2210.08856

Code (1)

wenhe-jia/tive 공식 구현

Tasks

Instance SegmentationSegmentationSemantic SegmentationVideo Instance Segmentation

Similar Papers 제목 키워드 기반

TIDE: A General Toolbox for Identifying Object Detection Errors

2020-08-18 · ECCV 2020 8 · Daniel Bolya, Sean Foley, James Hays, Judy Hoffman

We introduce TIDE, a framework and associated toolbox for analyzing the sources of error in object detection and instance segmentation algorithms. Importantly, our framework is applicable across datasets and can be appli…

Instance Segmentationobject-detectionObject DetectionSemantic Segmentation

Instance Embedding Transfer to Unsupervised Video Object Segmentation

2018-01-03 · CVPR 2018 6 · Siyang Li, Bryan Seybold, Alexey Vorobyov, Alireza Fathi 외

We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each p…

ObjectOptical Flow EstimationSegmentationSemantic Segmentation+3

S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation

2025-12-16 · Leon Sick, Lukas Hoyer, Dominik Engel, Pedro Hermosilla 외 arxiv

In recent years, the state-of-the-art in unsupervised video instance segmentation has heavily relied on synthetic video data, generated from object-centric image datasets such as ImageNet. However, video synthesis by art…

Unsupervised Instance SegmentationVideo Instance Segmentation

A2VIS: Amodal-Aware Approach to Video Instance Segmentation

2024-12-02 · Minh Tran, Thang Pham, Winston Bounsavy, Tri Nguyen 외

Handling occlusion remains a significant challenge for video instance-level tasks like Multiple Object Tracking (MOT) and Video Instance Segmentation (VIS). In this paper, we propose a novel framework, Amodal-Aware Video…

Instance SegmentationMultiple Object TrackingObjectObject Tracking+3

Identifying Surgical Instruments in Laparoscopy Using Deep Learning Instance Segmentation

2025-08-29 · Sabrina Kletz, Klaus Schoeffmann, Jenny Benois-Pineau, Heinrich Husslein arxiv

Recorded videos from surgeries have become an increasingly important information source for the field of medical endoscopy, since the recorded footage shows every single detail of the surgery. However, while video record…

Instrument RecognitionInstance Segmentation