AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Domain-Invariant Disentangled Network for Generalizable Object Detection

Chuang Lin, Zehuan Yuan, Sicheng Zhao, Peize Sun, Changhu Wang, Jianfei Cai

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 90 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 image-level disentanglement to Faster R-CNN (versus source-combined) (ablation)Faster R-CNN · Cityscapes target (DG)mAP@0.5 (%): 45.3 -> 47.1Improved
add instance-level disentanglement to Faster R-CNN (ablation)Faster R-CNN · Cityscapes target (DG)mAP@0.5 (%): 45.3 -> 46.1Improved
add instance-level disentanglement on top of image-level (ablation)DIDN · Cityscapes target (DG)mAP@0.5 (%): 47.1 -> 47.3Improved
add cross-level reconstruction on top of two-level disentanglement (ablation)DIDN · Cityscapes target (DG)mAP@0.5 (%): 47.3 -> 47.9Improved
add image-level disentanglement (ablation)Faster R-CNN · Foggy Cityscapes target (DG)mAP@0.5 (%): 31.3 -> 32.1Improved
add instance-level disentanglement (ablation)Faster R-CNN · Foggy Cityscapes target (DG)mAP@0.5 (%): 31.3 -> 31.9Mixed
add cross-level reconstruction on top of two-level disentanglement (ablation)DIDN · Foggy Cityscapes target (DG)mAP@0.5 (%): 33.2 -> 33.4Improved
add instance-level disentanglement on top of image-level (ablation)DIDN · Foggy Cityscapes target (DG)mAP@0.5 (%): 32.1 -> 33.2Improved
add cross-level reconstruction on top of two-level disentanglement (ablation)DIDN · BDD100k target (DG)mAP@0.5 (%): 22.2 -> 22.7Improved
add instance-level disentanglement on top of image-level (ablation)DIDN · BDD100k target (DG)mAP@0.5 (%): 21.1 -> 22.2Improved
directly align all source domains with a domain classifierFaster R-CNN · Foggy Cityscapes target (DG)mAP@0.5 (%): 31.3 -> 27.4Hurt
directly align all source domains with a domain classifierFaster R-CNN · BDD100k target (DG)mAP@0.5 (%): 18.9 -> 19.1No clear effect

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