AI Paper Atlas

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

Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes

Chenhongyi Yang, Vitaly Ablavsky, Kaihong Wang, Qi Feng, Margrit Betke

ECCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 12 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
replace Greedy-NMS with SG-NMS-LinearSerial R-FCN · KITTI val car (Hard)AP: 90.21 -> 92.54Improved
add SG-NMS to the Serial R-FCN baseline (ablation)Serial R-FCN · KITTI val car (Heavy occlusion)AP: 44.03 -> 52.62Improved
add self-attention branch to each head (ablation)Serial R-FCN · KITTI val car (Heavy occlusion)AP: 44.03 -> 47.79Improved
add self-attention branch to each head (ablation)Serial R-FCN · KITTI val car (Hard)AP: 89.30 -> 90.10Improved
add box noise during training (ablation)Serial R-FCN · KITTI val car (Heavy occlusion)AP: 44.03 -> 43.98No clear effect
add box noise during training (ablation)Serial R-FCN · KITTI val car (Hard)AP: 89.30 -> 90.01Improved
add self-attention when SG-NMS is used (ablation)Serial R-FCN + SG-NMS · KITTI val car (Heavy occlusion)AP: 52.62 -> 58.43Improved
add box noise on top of SG-NMS and attention (ablation)Serial R-FCN + SG-NMS + attention · KITTI val car (Heavy occlusion)AP: 58.43 -> 61.48Improved
add SG-NMS on top of noise and attention (ablation)Serial R-FCN + noise + attention · KITTI val car (Heavy occlusion)AP: 50.63 -> 61.48Improved
use semantics-geometry embedding instead of geometric-only embedding (ablation)SG-NMS · KITTI val car (Heavy occlusion)AP: 38.12 -> 61.48Improved
use semantics-geometry embedding instead of semantic-only embedding (ablation)SG-NMS · KITTI val car (Heavy occlusion)AP: 55.60 -> 61.48Improved
use SG-NMS-Square instead of Greedy-NMS best thresholdSerial R-FCN · KITTI val car (Heavy occlusion)AP: 57.21 -> 62.08Improved

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