AI Paper Atlas

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

CAT-Det: Contrastively Augmented Transformer for Multi-Modal 3D Object Detection

Yanan Zhang, Jiaxin Chen, Di Huang

CVPR 2022 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 4 citations (OpenAlex)

Check 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
Use CAT-Det's two-stream transformer, cross-modal fusion, and OMDAMulti-modal 3D detection · KITTI test splitmAP: 65.19 -> 67.05Improved
Use CAT-Det rather than Part-A²Multi-modal 3D detection · KITTI validation splitmAP: 72.20 -> 75.42Improved
Replace PointNet++ and 2D CNN with TPI while retaining concatenation (ablation)Baseline multi-modal detector · KITTI validation splitmAP: 68.65 -> 70.44Improved
Add CMT to TPI (ablation)TPI multi-modal detector · KITTI validation splitmAP: 70.44 -> 71.89Improved
Add OMDA to TPI + CMT (ablation)TPI + CMT detector · KITTI validation splitmAP: 71.89 -> 75.42Improved
Use CMT fusion instead of concatenation or attention-based fusion (ablation)TPI multi-modal detector · KITTI validation splitmAP: 70.44 -> 71.89Improved
Preserve single-modal features alongside cross-modal features in CMT (ablation)CMT fusion · KITTI validation splitmAP: 71.41 -> 71.89Improved
Add point-level contrastive augmentation (ablation)TPI + CMT detector · KITTI validation splitmAP: 71.89 -> 74.54Improved
Add object-level contrastive augmentation with background negatives (ablation)Point-level contrastive augmentation · KITTI validation splitmAP: 74.54 -> 75.00Improved
Select object-level negative pairs using a memory bank (ablation)Point-level contrastive augmentation · KITTI validation splitmAP: 74.54 -> 75.42Improved
Retain CMT at each of Layers 1–5 (ablation)CAT-Det · KITTI validation splitmAP: 75.15 -> 75.42; 74.86 -> 75.42; 74.42 -> 75.42; 74.55 -> 75.42; 74.13 -> 75.42Improved
Set the OMDA memory bank size to 1024 rather than 256, 512, 2048, or 4096 (ablation)CAT-Det OMDA · KITTI validation splitmAP: 75.14; 75.19; 75.42; 75.28; 75.06Mixed

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