AI Paper Atlas

Research map / Point clouds / Point cloud classification

CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network

Tao Xie, Ke Wang, Siyi Lu, Yukun Zhang, Kun Dai, Xiaoyu Li, Jie Xu, Li Wang, Lijun Zhao, Xinyu Zhang, Ruifeng Li

ICCV 2023 · Point clouds › Point cloud classification · approach: Efficient point sampling architectures · 11 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
replace searched subnet with random subnet under parameter constraint (ablation)CO-Net (base) · ScanObjectNN / S3DIS / SUN RGBDOA / mIoU / mAP: cls 87.3 -> 88.6, seg 63.6 -> 64.8, det 62.1 -> 62.9Improved
let each task have task-specific parameters instead of sharing all backbone parameters (ablation)CO-Net (base) · three tasksS-Score: 210.1 -> 216.1Improved
make normalization layers task-specific as well as conv layers (ablation)CO-Net (base) · three tasksS-Score: 214.4 -> 216.1 (EXP2 vs EXP3)No clear effect
add sign-based gradient surgery (ablation)CO-Net (base) · three tasksS-Score: 213.2 -> 216.1Improved
use sign-based gradient surgery instead of PCGrad (ablation)CO-Net (base) · three tasksS-Score: 215.1 -> 216.1Improved
use sign-based gradient surgery instead of DWA (ablation)CO-Net (base) · three tasksS-Score: 214.2 -> 216.1Improved
joint training and NAS versus individually trained searched architecture (ablation)CO-Net (base) · ScanObjectNN / S3DIS / SUN RGBDOA / mIoU / mAP: cls 88.6 -> 88.4, seg 64.8 -> 65.4, det 62.9 -> 62.6; params 4.300 -> 3.362Mixed
set lambda to 0.5 versus 0.25 and 0.75 (ablation)CO-Net (base) · three tasksS-Score: 215.4 / 215.5 -> 216.1Improved
freeze task-shared parameters and train only task-specific ones for a new taskCO-Net (base) · ModelNet40 incrementaloverall accuracy: 90.7 -> 92.1 with 62.15% extra parametersImproved
joint multi-task CO-Net versus segmentation-specialized modelsCO-Net · S3DIS Area 5mIoU / OA: CO-Net (large) 68.0 vs Point Transformer 70.4No clear effect

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