AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Ithaca365: Dataset and Driving Perception Under Repeated and Challenging Weather Conditions

Carlos A. Diaz-Ruiz, Youya Xia, Yurong You, Jose Nino, Junan Chen, Josephine Monica, Xiangyu Chen, Katie Luo, Yan Wang, Marc Emond, Wei-Lun Chao, Bharath Hariharan and 2 more

CVPR 2022 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 58 citations (OpenAlex)

Check 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 PAM, CAM, Mixture Pooling, and the residual sum operation to SFIAmodal road segmentation · Ithaca365 road testmIOU: 89.50 -> 92.19Improved
Train SFI on Ithaca365 rather than CityscapesSFI · KITTI road testmIOU: 66.29 -> 72.31Improved
Train SFI on Ithaca365 rather than CityscapesSFI · Cityscapes road testmIOU: 72.75 -> 74.68Improved
Train the road segmentation model on Ithaca365 rather than CityscapesSFI · Ithaca365 road testmIOU: 50.16 -> 89.50Improved
Train and test on the same weather condition rather than a different weather conditionMask R-CNN amodal instance segmentation · Ithaca365 weather-specific testsmAP@[.5:.95]: Table 4 diagonal entries are the highest for each test-weather columnImproved
Train PSMNet on the test weather rather than another weatherPSMNet stereo matching · Ithaca365 rain, snow, and nightThree-pixel-error (%): Table 6 diagonal errors are usually much smaller than cross-domain errorsImproved
Use the proposed amodal road model rather than SFIAmodal road segmentation · KITTI road testmIOU: 72.31 -> 72.25No clear effect
Use Mixture Pooling instead of Max Pooling as Inpainting (ablation)Amodal road segmentation · Qualitative inpainting resultsinpainting boundary smoothnessImproved
Add a residual sum link from the PAM output before the final up-sampling layer (ablation)Amodal road segmentation · Qualitative inpainting resultsinpainting qualityImproved
Add the residual sum link from PAM (ablation)Amodal road segmentation · Images where foreground objects occupy a relatively large spaceinpainting qualityImproved

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