AI Paper Atlas

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

FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration

Zhijian Huang, Sihao Lin, Guiyu Liu, Mukun Luo, Chaoqiang Ye, Hang Xu, Xiaojun Chang, Xiaodan Liang

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 9 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 intra- and inter-gradient calibration to the multi-task baselineBEVFusion-based multi-task baseline · nuScenes val, det:seg=1:1delta_MTL (%): 18.3 -> 5.4Improved
add inter-gradient calibration (IMTL-G on task gradients) (ablation)multi-task baseline · nuScenes val, det:seg=1:1mIoU (%): 44.0 -> 59.5Improved
add inter-gradient calibration alone (ablation)multi-task baseline · nuScenes val, det:seg=1:1mAP (%): 59.1 -> 57.1Hurt
add intra-gradient calibration (balance LiDAR and image gradients) (ablation)multi-task baseline · nuScenes val, det:seg=1:1mAP / mIoU: mAP 59.1 -> 59.5, mIoU 44.0 -> 45.0Improved
manually raise segmentation loss weight from 5 to 10 (ablation)multi-task baseline · nuScenes valmAP / mIoU: mIoU 55.7 -> 57.9, mAP 59.8 -> 59.3Mixed
add calibration across disjoint annotation settings (ablation)multi-task baseline · nuScenes Disjoint-balance and Disjoint-normaldelta_MTL (%): 21.3 -> 9.8 (balance); 19.3 -> 9.7 (normal)Improved
apply either calibration alone (ablation)multi-task baseline · nuScenes valgamma_task / gamma_modal: gamma_task 19.2 -> 2.5 (inter only)Improved
share backbone for multi-task Fuller instead of separate single-task modelsFuller · nuScenes inferencememory and FPS: 6144MB -> 3103MB; 1.20 -> 2.30 FPSImproved
extend to a third task (foreground segmentation)Fuller · nuScenes val, 3 tasksdelta_MTL (%): 12.8 -> 9.9Improved

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