AI Paper Atlas

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

A Dynamic Feature Interaction Framework for Multi-task Visual Perception

Yuling Xi, Hao Chen, Ning Wang, Peng Wang, Yanning Zhang, Chunhua Shen, Yifan Liu

IJCV 2023 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 10 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 Message Passing (DMP) to the two-branch baseline (ablation)D2BNet · Cityscapes val multi-taskDS: 45.38 -> 45.73Improved
add task-aware dynamic router (TDR) to DMP (ablation)D2BNet · Cityscapes val multi-taskDS: 45.73 -> 47.09Improved
add channel-aware dynamic router (CDR) to DMP (ablation)D2BNet · Cityscapes val multi-taskDS: 45.73 -> 47.6Improved
add CDR on top of DMP and TDR (ablation)D2BNet · Cityscapes val multi-taskPQ: 58.13 -> 58.6Improved
add DMP for single-task panoptic segmentation (ablation)D2BNet · Cityscapes panoptic (single task)PQ: 58.7 -> 60.0Improved
co-train panoptic segmentation with depth (no dynamic modules) (ablation)D2BNet · Cityscapes valPQ: 58.23 -> 56.40Hurt
co-train depth with segmentation (no dynamic modules) (ablation)D2BNet · Cityscapes valAbs. Rel.: 0.124 -> 0.111Improved
alternate training over nuScenes and nuImagesD2BNet · nuScenes3D mAP: 28.79 -> 30.63Improved
alternate training over nuScenes and nuImagesD2BNet · nuImagesmask mAP: 42.28 -> 39.81Hurt
compute context information from box tower instead of no context (ablation)D2BNet · COCO instance segmentation (ablation)AP: 34.7 -> 35.2Improved
use factored attention instead of channel-wise vector attention (ablation)D2BNet · COCO instance segmentation (ablation)AP: 35.2 -> 36.3Improved
double dense branch width from 32 to 64 (ablation)D2BNet · COCO panoptic (R-50, 3x)PQ: 41.8 -> 42.9Improved

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