AI Paper Atlas

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

Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection

Deepti Hegde, Suhas Lohit, Kuan-Chuan Peng, Michael J. Jones, Vishal M. Patel

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 0 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 spatial equivariance to temporal-only pretraining (ablation)VoxelRCNN pretraining · KITTI 5% labelsmAP (%): 65.82 -> 66.52Improved
add temporal (scene flow) equivariance to spatial-only pretraining (ablation)VoxelRCNN pretraining · KITTI 5% labelsmAP (%): 66.01 -> 66.52Improved
use both objectives instead of spatial-only for pedestrian (ablation)VoxelRCNN pretraining · KITTI 5% labels, Pedestrian moderate APAP (%): 50.34 -> 48.55Hurt
use classification objective for rotation equivariance instead of PointInfoNCE contrastive (ablation)SECOND pretraining · KITTI SECONDrelative mAPImproved
use contrastive objective for translation and scaling equivariance instead of classification (ablation)SECOND pretraining · KITTI SECONDrelative mAPImproved
pretrain with equivariant spatio-temporal SSL with 20% labelsSECOND · KITTI 20% vs 100% no pretrainingmAP (%): 61.86 -> 65.28Improved
pretrain with the method when full labels are availableVoxelRCNN · KITTI 100% labels (Waymo pretrain)mAP (%): 71.77 -> 70.56Hurt
pretrain with the method versus invariant STRL baselineSECOND · KITTI 5% labels (KITTI-360 pretrain)mAP (%): 52.94 -> 58.60Improved
pretrain with the method on KITTI Car categorySECOND / VoxelRCNN · KITTI Car APAP (%)No clear effect
method versus ALSO generative pretrainingSECOND · KITTI 5% labelsmAP (%): 59.69 -> 58.60Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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