AI Paper Atlas

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

Rain Rendering for Evaluating and Improving Robustness to Bad Weather

Maxime Tremblay, Shirsendu Sukanta Halder, Raoul de Charette, Jean‐François Lalonde

IJCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Remote sensing segmentation and change · 144 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
fine-tune YOLOv2 on PBR rain with curriculumYOLOv2 · real nuScenes-rainmAP (%): 16.30 -> 19.68 (+20.7%)Improved
fine-tune YOLOv2 on GAN rainYOLOv2 · real nuScenes-rainmAP (%): 16.30 -> 18.07 (+10.9%)Improved
fine-tune YOLOv2 on GAN+PBR rainYOLOv2 · real nuScenes-rainmAP (%): 16.30 -> 19.73 (+21.0%)Improved
fine-tune PSPNet on PBR rainPSPNet · real nuScenes-rainAP (%): 18.7 -> 25.6 (+36.9%)Improved
fine-tune Monodepth2 on PBR rainMonodepth2 · real nuScenes-rainSq. rel. err. (%): 3.53 -> 3.54 (0.0%)No clear effect
fine-tune Monodepth2 on GAN+PBR rainMonodepth2 · real nuScenes-rainSq. rel. err. (%): 3.53 -> 3.29 (+8.2%)Improved
fine-tune PSPNet on PBR rain, effect on clear imagesPSPNet · real nuScenes-clearAP (%): 40.8 -> 39.0Hurt
fine-tune YOLOv2 with rain curriculum (PBR), robustness at 200 mm/hrYOLOv2 · nuScenes-augment PBRmAP (%): 20.4 -> 31.0Improved
fine-tune PSPNet with rain curriculum, at 100 mm/hrPSPNet · Cityscapes PBR 100 mm/hrAP (%): 52.0 -> 54.0Improved
fine-tune YOLOv2 on hybrid GAN+PBR at 100 mm/hrYOLOv2 · nuScenes-augment GAN+PBR 100 mm/hrmAP (%): 7.5 -> 21.7Improved
fine-tune Monodepth2 on hybrid GAN+PBR at 100 mm/hrMonodepth2 · nuScenes-augment GAN+PBR 100 mm/hrSq. rel. err. (%): 8.9 -> 5.7Improved
de-rain input with DualResNet instead of rain-aware finetuning, depthMonodepth2 · real nuScenes-rainSq. rel. err. (%): 3.29 -> 3.09Improved

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