AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model

Xiuye Gu, Yin Cui, Jonathan Huang, Abdullah Rashwan, Xuan Yang, Xingyi Zhou, Golnaz Ghiasi, Weicheng Kuo, Huizhong Chen, Liang-Chieh Chen, David A Ross

NeurIPS 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 10 citations (OpenAlex)

Read the paper

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
Co-train across ADE semantic, COCO panoptic, and Objects365 detection instead of training a separate model per datasetDaTaSeg with ResNet50 · ADE semanticmIoU: 42.0 -> 48.1 (+6.1)Improved
Co-train across ADE semantic, COCO panoptic, and Objects365 detection instead of training a separate model per datasetDaTaSeg with ResNet50 · COCO panopticPQ: 48.2 -> 49.0 (+0.8)Improved
Transfer knowledge from COCO panoptic while training ADE semantic supervisionDaTaSeg with ResNet50 · ADE semantic to panopticPQ: 26.9 -> 29.8 (+2.9)Improved
Transfer instance-segmentation knowledge from COCO panoptic during box-supervised trainingDaTaSeg with ResNet50 · Objects365 box to instancemask AP: 12.3 -> 14.3 (+2.0)Improved
Increase segment queries from 100 to 150 (ablation)DaTaSeg with ResNet50 · ADE semanticmIoU: 48.1 -> 48.7Improved
Increase segment queries from 100 to 150 (ablation)DaTaSeg with ResNet50 · COCO panopticPQ: 49.0 -> 48.9No clear effect
Increase segment queries from 100 to 150 (ablation)DaTaSeg with ResNet50 · ADE semantic to panopticPQ: 29.8 -> 29.1Hurt
Increase segment queries from 100 to 150 (ablation)DaTaSeg with ResNet50 · Objects365 box to instanceAP: 14.3 -> 15.8Improved
Add dataset-specific queries, classification heads, and background classifiers (ablation)DaTaSeg with ResNet50 · COCO panopticPQ: 49.0 -> 46.0 (-3.0)Hurt
Add dataset-specific queries, classification heads, and background classifiers (ablation)DaTaSeg with ResNet50 · ADE semantic to panopticPQ: 29.8 -> 26.9 (-2.9)Hurt
Add dataset-specific queries, classification heads, and background classifiers (ablation)DaTaSeg with ResNet50 · Objects365 box to instanceAP: 14.3 -> 10.9 (-3.4)Hurt
Use 30 dataset-specific queries rather than none (ablation)DaTaSeg with ResNet50 · COCO panopticPQ: 48.1 -> 45.8Hurt

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