AI Paper Atlas

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

Enhancing Multi-modal Features Using Local Self-Attention for 3D Object Detection

Hao Li, Zehan Zhang, Xian Zhao, Yulong Wang, Yuxi Shen, Shiliang Pu, Hui Mao

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Camera-radar fusion detection · 8 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 camera features by naive concatenation fusion to range-only detector (ablation)EMMF-Det range baseline · Waymo val (20% train)All AP L1: 72.7 -> 73.3Improved
add local self-attention feature re-weighting fusion instead of naive concatenation (ablation)EMMF-Det · Waymo val (20% train)All AP L1: 73.3 -> 74.3Improved
add local self-attention feature re-weighting fusion to range-only detector (ablation)EMMF-Det · Waymo val (20% train)All AP L2: 64.3 -> 66.4Improved
increase neighborhood size k from 8 to 16 in fusion candidate sets (ablation)EMMF-Det · Waymo val (20% train)All AP L1: 74.3 -> 73.9Hurt
k=16 still beats naive concatenation (ablation)EMMF-Det · Waymo val (20% train)All AP L1: 73.3 -> 73.9Improved
add multi-modal copy-paste augmentation (ablation)EMMF-Det · Waymo val (20% train)All AP L1: 71.3 -> 73.0Improved
use linear combination of pixels instead of direct pasting in camera copy-paste (ablation)EMMF-Det · Waymo val (20% train)All AP L1: 73.0 -> 73.3Improved
add noise jitter on range images (ablation)EMMF-Det · Waymo val (20% train)All AP L1: 73.3 -> 74.3Improved
add noise jitter on range images (ablation)EMMF-Det · Waymo val (20% train)All AP L2: 65.3 -> 66.4Improved
add IoU prediction moduleEMMF-Det · Waymo val (full training)All AP L1: 76.9 -> 78.8Improved

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