AI Paper Atlas

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

Efficient Transformer-based 3D Object Detection with Dynamic Token Halting

Mao Ye, Gregory P. Meyer, Yuning Chai, Qiang Liu

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 12 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 dynamic token halting (SST_halt) to SST_centerSST_center · Waymo val vehicle BEV AP [50, inf) L2BEV AP: 40.8 -> 41.2Improved
add improvements on top of halting (SST++halt)SST_center · Waymo val vehicle BEV AP [50, inf) L2BEV AP: 40.8 -> 43.4Improved
add voxel (token) recycling for halted tokens (ablation)SST++halt · Waymo valVehicle L1 AP: 61.9 -> 75.7Improved
add voxel recycling (ablation)SST++halt · Waymo valCyclist L1 AP: 63.7 -> 70.0Improved
add voxel recycling (ablation)SST++halt · Waymo valPedestrian L1 AP: 76.8 -> 78.7Improved
use non-uniform sparsity loss instead of uniform l1 (ablation)SST++halt · Waymo valVehicle L1 AP: 74.5 -> 75.7Improved
use non-uniform sparsity loss instead of uniform l1 (ablation)SST++halt · Waymo valCyclist L1 AP: 64.2 -> 70.0Improved
use non-uniform sparsity loss instead of uniform l1 (ablation)SST++halt · Waymo valPedestrian L2 AP: 70.2 -> 72.3Improved
dynamic token halting vs width scaling at similar speedup (~1.1-1.2x)SST_center · Waymo valVehicle L1 AP: 73.8 -> 76.1Improved
dynamic token halting vs adapted AViT at ~1.4x speedupSST_center · Waymo valVehicle L1 AP: 70.3 -> 76.1Improved
token halting at 1.52x speedup (sparsity 0.89) vs originalSST_center · Waymo valVehicle L1 AP: 76.2 -> 75.4Mixed
apply SST++halt in place of SST_center on test splitSST_center · Waymo testVehicle L1 AP: 80.0 -> 81.2Improved

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