AI Paper Atlas

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

Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights

Yan Hao, Florent Forest, Olga Fink

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 22 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 batch normalization layers to the VGG16 backbone (source-only) (ablation)Faster-RCNN source-only · Cityscapes->Foggy-CityscapesmAP@0.5: 20.0 -> 26.9Improved
add batch normalization layers to the VGG16 backbone (source-only) (ablation)Faster-RCNN source-only · SIM10k->CityscapesAP on car: 31.0 -> 31.5No clear effect
adapt batch statistics on target train data (AdaBN)source model with BN · SIM10k->CityscapesAP on car: 31.5 -> 46.9Improved
adapt batch statistics on target train data (AdaBN)source model with BN · Cityscapes->Foggy-CityscapesmAP@0.5: 26.9 -> 35.1Improved
enable regression losses on unlabeled target samples (ablation)SF-UT · Cityscapes->Foggy-CityscapesmAP@0.5: 43.3 -> 45.0Improved
add AdaBN before generating fixed pseudo-labels (ablation)Fixed SF-FixMatch · Cityscapes->Foggy-CityscapesmAP@0.5: 39.0 -> 44.5Improved
add AdaBN before generating fixed pseudo-labels (ablation)Fixed SF-PL · Cityscapes->Foggy-CityscapesmAP@0.5: 35.6 -> 38.5Improved
add weak-strong augmentation to AdaBN + Fixed SF-PL (ablation)AdaBN + Fixed SF · Cityscapes->Foggy-CityscapesmAP@0.5: 38.5 -> 44.5Improved
add weak-strong augmentation to Mean Teacher (giving SF-UT) (ablation)Mean Teacher · Cityscapes->Foggy-CityscapesmAP@0.5: 38.2 -> 45.0Improved
use fixed pseudo-labels instead of updated ones (ablation)SF-FixMatch · Cityscapes->Foggy-CityscapesmAP@0.5: 36.8 -> 39.0Improved
add Mosaic augmentation on top of strong augmentation (ablation)AdaBN + Fixed SF-FM · Cityscapes->Foggy-CityscapesmAP@0.5: 44.5 -> 44.6No clear effect
add Mosaic augmentation on top of strong augmentation (ablation)AdaBN + Fixed SF-PL · Cityscapes->Foggy-CityscapesmAP@0.5: 38.5 -> 40.7Improved

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