AI Paper Atlas

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

Unsupervised Domain Adaptive Detection with Network Stability Analysis

Wenzhang Zhou, Heng Fan, Tiejian Luo, Libo Zhang

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 17 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
add Network Stability Analysis (HID+LID+InsD) with teacher-student and pseudo-label stage S3Faster R-CNN baseline w. data aug. · Cityscapes->FoggyCityscapesmAP: 34.2 -> 52.7Improved
add heavy image-level disturbance (HID) consistency (ablation)NSA-UDA · Cityscapes->FoggyCityscapes (S2)mAP: 34.2 -> 44.2Improved
add light image-level disturbance (LID) on top of HID (ablation)NSA-UDA · Cityscapes->FoggyCityscapes (S2)mAP: 44.2 -> 48.9Improved
add instance-level disturbance (InsD) on top of HID and LID (ablation)NSA-UDA · Cityscapes->FoggyCityscapes (S2)mAP: 48.9 -> 49.6Improved
add external consistency analysis (ECA) to NSA_LID (ablation)NSA-UDA · Cityscapes->FoggyCityscapes (S2)mAP: 45.9 -> 47.2Improved
add internal consistency analysis (ICA) to NSA_LID (ablation)NSA-UDA · Cityscapes->FoggyCityscapes (S2)mAP: 45.9 -> 48.7Improved
apply NSA's disturbances to PT instead of its original perturbation (ablation)PT · Cityscapes->FoggyCityscapesmAP: 42.7 -> 44.9Improved
add pseudo-label stage S3 after source-only NSA stage S2 (ablation)NSA-UDA · KITTI->FoggyCityscapesmAP: 41.9 -> 50.0Improved
apply NSA (stage S2) using source data only (ablation)Faster R-CNN baseline w. data aug. · SIM10k->CityscapesAP car: 44.2 -> 52.2Improved
plug NSA into one-stage FCOS detectorFCOS · Cityscapes->FoggyCityscapesmAP: 21.0 -> 44.2Improved
compare NSA-UDA with PT on KITTI->CityscapesNSA-UDA · KITTI->CityscapesAP car: 60.2 (PT) vs 55.6Hurt
vary LID loss weight gamma_LID (ablation)NSA-UDA · Cityscapes->FoggyCityscapes (S2)mAP: 48.3 / 49.6 / 49.2 / 48.7 over 6e-4 to 6e-1Mixed

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