AI Paper Atlas

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

Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots

Qi Chen, Lin Sun, Zhixin Wang, Kui Jia, Alan Yuille

ECCV 2020 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 195 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 quadrant spatial relation encoder (ablation)HotSpotNet · KITTI val Cyclist ModerateAP: 69.31 -> 72.55Improved
add quadrant spatial relation encoder (ablation)HotSpotNet · KITTI val Car ModerateAP: 82.27 -> 82.75Improved
add quadrant spatial relation encoder (ablation)HotSpotNet · KITTI val Cyclist EasyAP: 89.48 -> 88.22Hurt
add soft argmin for regression (ablation)HotSpotNet · KITTI val Cyclist ModerateAP: 68.65 -> 72.55Improved
add soft argmin for regression (ablation)HotSpotNet · KITTI val Pedestrian ModerateAP: 63.7 -> 65.9Improved
limit hotspots per object to C=64 instead of all non-empty spots (ablation)HotSpotNet · KITTI val Cyclist ModerateAP: 67.66 -> 72.55Improved
limit hotspots per object to C=64 instead of all non-empty spots (ablation)HotSpotNet · KITTI val Pedestrian ModerateAP: 62.08 -> 65.9Improved
limit hotspots per object to C=64 instead of all non-empty spots (ablation)HotSpotNet · KITTI val Car ModerateAP: 82.93 -> 82.75No clear effect
assign all non-empty spots rather than all voxels as hotspots (ablation)HotSpotNet · KITTI val Pedestrian ModerateAP: 62.82 -> 62.08No clear effect
use eight-direction spatial encoding instead of quadrants (ablation)HotSpotNet · KITTI val Cyclist ModerateAP: 72.55 -> 69.99Hurt
use left and right encoding instead of none (ablation)HotSpotNet · KITTI val Pedestrian ModerateAP: 65.45 -> 64.05Hurt
use deviation regression instead of quadrant classification (ablation)HotSpotNet · KITTI val Car ModerateAP: 82.75 -> 82.03Hurt

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