AI Paper Atlas

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

UFO²: A Unified Framework towards Omni-supervised Object Detection

Zhongzheng Ren, Zhiding Yu, Xiaodong Yang, Ming-Yu Liu, Alexander G. Schwing, Jan Kautz

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection

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 teacher loss L_T1 (ablation)UFO2 (boxes) · COCO-val, VGG-16AP: 22.6 -> 24.8Improved
add teacher loss L_T2 (ablation)UFO2 (boxes) · COCO-val, VGG-16AP: 22.6 -> 25.1Improved
add L_T1 and L_T2 (ablation)UFO2 (boxes) · COCO-val, VGG-16AP: 22.6 -> 25.5Improved
add tag teacher loss to L_T1 and L_T2 (ablation)UFO2 (boxes) · COCO-val, VGG-16AP: 25.5 -> 25.7Improved
add proposal refinement for points (Ref_P) (ablation)UFO2 (points) · COCO-val, VGG-16AP: 10.8 -> 11.1Improved
add proposal refinement for scribbles (Ref_S) (ablation)UFO2 (scribbles) · COCO-val, VGG-16AP: 10.8 -> 11.6Improved
add localization constraint for points (Con_P) (ablation)UFO2 (points) · COCO-val, VGG-16AP: 11.1 -> 12.4Improved
add localization constraint for scribbles (Con_S) (ablation)UFO2 (scribbles) · COCO-val, VGG-16AP: 11.6 -> 13.7Improved
add unlabeled data to fine-tune weakly supervised modelUFO2 ResNet-50 (tags) · COCO minivalAP: 9.8 -> 10.5Improved
add scribbles to fine-tune box-supervised modelUFO2 ResNet-50 (boxes) · COCO minivalAP: 29.1 -> 30.9Improved
add tags to fine-tune box-supervised modelUFO2 ResNet-50 (boxes) · COCO minivalAP: 29.1 -> 29.4Improved
train with 80% boxes budget instead of mostly tagsUFO2 · COCO budget policyAP: 3.0 ± 0.57 -> 14.11 ± 1.01Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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