AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Enriching Information and Preserving Semantic Consistency in Expanding Curvilinear Object Segmentation Datasets

Qin Lei, Jiang Zhong, Qizhu Dai

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 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
replace GroupNorm with SPADE in ControlNet encoder blocks (SCP ControlNet) (ablation)ControlNet for semantic image synthesis · Crack500 5x expanded, UNetmIoU: 75.4 -> 78.4Improved
add SPADE in Down.3 encoder block (on top of Down.1-2) (ablation)SCP ControlNet · Crack500 5x expanded, UNetmIoU: 75.9 -> 77.9Improved
add SPADE in Middle block on top of Down.1-4 (ablation)SCP ControlNet · Crack500 5x expanded, UNetmIoU: 78.2 -> 78.4Improved
apply SPADE only in the early encoder blocks (Down.1 or Down.2) (ablation)SCP ControlNet · Crack500 5x expanded, UNetmIoU: 75.4 -> 75.7 (Down.1), 75.5 (Down.2)No clear effect
expand dataset 5x with SCP ControlNet synthetic data vs training on originalUNet trained from scratch · CHUACmIoU: 51.2 -> 61.5Improved
expand with RandAugment 5xUNet on DRIVE · DRIVEmIoU: 68.6 -> 67.2Hurt
use SCP ControlNet instead of vanilla ControlNet for expansiondataset expansion across segmentation architectures · Crack500, DeepLabV3+mIoU: 76.8 -> 78.1Improved
use SCP ControlNet vs CE (GAN-based) with DeepLabV3+ on XCADdataset expansion · XCAD, DeepLabV3+mIoU: 85.7 (CE) vs 84.3Hurt
use SCP ControlNet vs CE for F1 on CHASEDB1dataset expansion, UNet · CHASEDB1F1: 81.5 (CE) vs 81.2No clear effect
expansion with synthetic data on Mask2Former for DRIVE and CHUACMask2Former · DRIVE and CHUACmIoU: DRIVE 66.3 -> 67.1; CHUAC 50.1 -> 57.1 with SCP ControlNetMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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