atlas

Research map / Detection and segmentation / CNN features

Rich Context Aggregation With Reflection Prior for Glass Surface Detection

CVPR 2021 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 78 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
use RCAM and RRM instead of TransLabglass-surface detection model · Trans10K testIoU: 86.13 -> 89.16Helped
use RCAM and RRM instead of MINetglass-surface detection model · GDD testIoU: 84.35 -> 88.07Helped
use RCAM and RRM instead of GDNetglass-surface detection model · GSD testIoU: 79.01 -> 83.64Helped
add multi-scale contextual contrast features (PCM) (ablation)Basic ResNeXt-101 model · GSD testIoU: 80.12 -> 81.56Helped
add two-level attention to RCAM contextual features (ablation)Basic + PCM model · GSD testIoU: 81.56 -> 82.36Helped
add the full RCAM (ablation)Basic ResNeXt-101 model · GSD testIoU: 80.12 -> 82.36Helped
add RRM without RCAM (ablation)Basic ResNeXt-101 model · GSD testIoU: 80.12 -> 81.11Helped
add RRM to a model with RCAM (ablation)Basic + RCAM model · GSD testIoU: 82.36 -> 83.64Helped

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