AI Paper Atlas

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

Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions

Vishwanath A. Sindagi, Poojan Oza, Rajeev Yasarla, Vishal M. Patel

ECCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 209 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 domain adversarial alignment after conv5 (ablation)Faster R-CNN · Cityscapes -> Foggy-CityscapesmAP: 24.4 -> 30.0Improved
add residual feature recovery block after conv4 (ablation)FRCNN+D5 · Cityscapes -> Foggy-CityscapesmAP: 30.0 -> 32.9Improved
replace domain adversarial loss with prior-adversarial loss (ablation)FRCNN+D5+R5 · Cityscapes -> Foggy-CityscapesmAP: 32.9 -> 36.5Improved
extend prior alignment and RFRB to conv4 and conv5 (ablation)FRCNN+P5+R5 · Cityscapes -> Foggy-CityscapesmAP: 36.5 -> 39.3Improved
align domain at two scales without RFRB (domain loss) (ablation)FRCNN+D5 · Cityscapes -> Foggy-CityscapesmAP: 30.0 -> 33.2Improved
align prior at two scales without RFRB (ablation)FRCNN+P5+R5 · Cityscapes -> Foggy-CityscapesmAP: 36.5 -> 37.4Improved
use ResNet-152 backbone instead of VGG16 for full method (ablation)FRCNN+P45+R45 · Cityscapes -> Foggy-CityscapesmAP: 39.3 -> 40.0Improved
add domain adversarial alignment after conv5 (ablation)Faster R-CNN · Cityscapes -> Rainy-CityscapesmAP: 21.8 -> 30.2Improved
add residual feature recovery block (ablation)FRCNN+D5 · Cityscapes -> Rainy-CityscapesmAP: 30.2 -> 31.2Improved
replace domain adversarial loss with prior-adversarial loss (ablation)FRCNN+D5+R5 · Cityscapes -> Rainy-CityscapesmAP: 31.2 -> 33.8Improved
extend prior alignment and RFRB to conv4 and conv5 (ablation)FRCNN+P5+R5 · Cityscapes -> Rainy-CityscapesmAP: 33.8 -> 36.1Improved
preprocess with Grid-Dehaze before detectionFaster R-CNN · Cityscapes -> RTTSmAP: 30.9 -> 20.0Hurt

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