AI Paper Atlas

Research map / Detection and segmentation / CNN features

Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning

Junwen He, Yifan Wang, Lijun Wang, Huchuan Lu, Bin Luo, Jun-Yan He, Jin-Peng Lan, Yifeng Geng, Xuansong Xie

ICCV 2023 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 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
replace depth regression head with instance-wise depth decoder using unified queries (ablation)DeepDPS (ResNet-50) · Cityscapes-DVPSDPQ: 60.3 -> 62.1Improved
add backup query for blank mask regions (ablation)DeepDPS (ResNet-50) · Cityscapes-DVPSDPQ: 62.1 -> 62.4Improved
add semantic-to-depth guidance (ablation)DeepDPS (ResNet-50) · Cityscapes-DVPSDPQ: 62.4 -> 62.8Improved
add depth-to-semantic guidance (ablation)DeepDPS (ResNet-50) · Cityscapes-DVPSDPQ: 62.8 -> 63.0Improved
add bi-directional guidance under incomplete supervision (ablation)DeepDPS (semi-supervised) · Cityscapes-DVPS incomplete labelsDPQ: 55.8 -> 57.8Improved
train with incomplete supervision labels instead of full supervision (ablation)DeepDPS · Cityscapes-DVPSDPQ: 58.5 -> 55.8Hurt
choose different guidance loss designs (SGT, DGS, ours) (ablation)DeepDPS guidance learning · Cityscapes-DVPSDPQ: 57.5 -> 58.0 (SGT), 58.2 (ours)Improved
use learned latent representation for geometric query enhancement instead of single query (ablation)DeepDPS · Cityscapes-DVPSDPQ: 53.3 -> 58.5Improved
add a second latent representation for semantic features (ablation)DeepDPS · Cityscapes-DVPSDPQ: 58.5 -> 57.4Hurt
Ours (Swin-B) versus PolyphonicFormer (Swin-B) at lambda=0.5DeepDPS · Cityscapes-DVPSDPQ (lambda=0.5): 70.6 vs 69.8; lambda=0.1 55.0 vs 50.2Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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