AI Paper Atlas

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

Depth-discriminative Metric Learning for Monocular 3D Object Detection

Wonhyeok Choi, Mingyu Shin, Sunghoon Im

NeurIPS 2023 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 2 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 quasi-isometric loss and object-wise depth lossMonoCon · KITTI val Car EasyAP_3D|R40: 23.03 -> 27.90Improved
add both lossesDID-M3D (LiDAR) · KITTI val Car ModerateAP_3D|R40: 16.22 -> 17.12Improved
add quasi-isometric loss only (ablation)MonoCon · KITTI valoverall AP gain: +8.7%Improved
add object-wise depth loss only (ablation)MonoCon · KITTI valoverall AP gain: +5.0%Improved
add quasi-isometric loss only (ablation)DID-M3D · KITTI valoverall AP gain: +2.3%Improved
use SupCR instead of quasi-isometric loss (ablation)MonoCon · KITTI val Car ModerateAP_3D|R40: 17.84 -> 17.55Hurt
use SupCR contrastive regression (ablation)MonoCon · KITTI valE_dim: 0.025 -> 0.031Hurt
apply to anchor-based MonoDTRMonoDTR · KITTI val Car ModerateAP_3D|R40: 18.45 -> 19.07Improved
apply to BEV ImVoxelNetImVoxelNet · KITTI val Car ModerateAP_3D|R40: 17.80 -> 18.20Improved
K = 2.0 instead of 1.5 (ablation)quasi-isometric loss on MonoCon · KITTI val Car ModerateAP_3D|R40: 18.68 -> 17.44Hurt
K = 1.0 instead of 1.5 (ablation)quasi-isometric loss on MonoCon · KITTI val Car ModerateAP_3D|R40: 18.68 -> 18.09Hurt
epsilon = infinity instead of 10 (ablation)quasi-isometric loss on MonoCon · KITTI val Car ModerateAP_3D|R40: 18.68 -> 16.91Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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