AI Paper Atlas

Research map / Video / Video segmentation and tracking

TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation

rongkun Zheng, Lu Qi, Xi Chen, Yi Wang, Kun Wang, Yu Qiao, Hengshuang Zhao

NeurIPS 2023 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add taxonomy compilation and injection to Mask2Former-VISMask2Former-VIS · YouTube-VIS 2019 valAP: 46.4 -> 49.7Improved
Add taxonomy compilation and injection to Mask2Former-VISMask2Former-VIS · YouTube-VIS 2021 valAP: 40.6 -> 44.9Improved
Add taxonomy compilation and injection to Mask2Former-VISMask2Former-VIS · OVIS valAP: 16.5 -> 22.8Improved
Add taxonomy compilation and injection to Mask2Former-VISMask2Former-VIS · UVO valAP: 18.2 -> 21.2Improved
Add taxonomy-aware matching loss (ablation)TMT-VIS · YouTube-VIS 2019 valAP: 47.0 -> 47.3Improved
Add taxonomy-aware matching loss (ablation)TMT-VIS · YouTube-VIS 2019 val, multiple datasetsAP: 49.2 -> 49.7Improved
Use taxonomy embedding set size 10 rather than 1 (ablation)TMT-VIS · YouTube-VIS 2019 val, multiple datasetsAP: 47.1 -> 49.7Improved
Increase taxonomy embedding set size from 10 to 100 (ablation)TMT-VIS · YouTube-VIS 2019 val, multiple datasetsAP: 49.7 -> 47.2Hurt
Replace cross-attention with addition for taxonomy injection (ablation)TMT-VIS · YouTube-VIS 2019 val, multiple datasetsAP: 49.7 -> 47.6Hurt
Replace cross-attention with concatenation for taxonomy injection (ablation)TMT-VIS · YouTube-VIS 2019 val, multiple datasetsAP: 49.7 -> 47.4Hurt
Use sampling ratio 1:1:0.75 instead of 2:1:0.75 (ablation)TMT-VIS · YouTube-VIS 2019 val, multiple datasetsAP: 48.6 -> 49.7Improved
Use sampling ratio 1:1:1 instead of 1:1:0.75 (ablation)TMT-VIS · YouTube-VIS 2019 val, multiple datasetsAP: 49.7 -> 49.5Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy