AI Paper Atlas

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

The Devil Is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection

Zhikang Zou, Xiaoqing Ye, Liang Du, Xianhui Cheng, Xiao Tan, Li Zhang, Jianfeng Feng, Xiangyang Xue, Errui Ding

ICCV 2021 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 54 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 self-reflect (S-R) module (ablation)M3D-RPN baseline · KITTI val1 Car (R40)AP_3D Mod.: 11.07 -> 13.08Improved
add self-reflect module on top of mutual-reflect (ablation)M3D-RPN + M-R · KITTI val1 Car (R40)AP_3D Mod.: 13.01 -> 13.39Improved
combine S-R and M-R rather than either alone (ablation)ALFR · KITTI val1 Car (R40)AP_3D Mod.: 13.08 -> 13.39Improved
add DIT module to ALFR (ablation)DFR-Net · KITTI val1 Car (R40)AP_3D Mod.: 13.39 -> 14.79Improved
assign rotation and dimensions to appearance stream instead of localization (ablation)DFR-Net · KITTI val1 Car (R40)AP_3D Mod.: 13.35 -> 14.79Improved
assign rotation to appearance rather than localization task (ablation)DFR-Net · KITTI val1 Car (R40)AP_3D Mod.: 13.35 -> 14.31Improved
add appearance-to-localization information flow (ablation)DFR-Net · KITTI val1 Car (R40)AP_3D Mod.: 13.46 -> 13.64Improved
add localization-to-appearance information flow (ablation)DFR-Net · KITTI val1 Car (R40)AP_3D Mod.: 13.46 -> 13.73Improved
use fixed initialized trading scores (DIT-init) instead of no DIT (ablation)DFR-Net · KITTI val1 Car (R40)AP_3D Mod.: 13.39 -> 14.07Improved
generate trading scores cross-task (DIT-cross) (ablation)DFR-Net · KITTI val1 Car (R40)AP_3D Mod.: 13.39 -> 12.44Hurt
add DIT scores from the task's own features instead of shared features (ablation)DFR-Net · KITTI val1 Car (R40)AP_3D Mod.: 13.87 -> 14.79Improved
apply DFR-Net to M3D-RPN backboneM3D-RPN · KITTI val1 CarAP_3D Easy: 14.53 -> 19.55Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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