AI Paper Atlas

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

A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing

Paul Upchurch, Ransen Niu

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 36 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
train on DMS data instead of OpenSurfaces (same architecture)ResNet-50 dilated + PPM · DMS-Val (25 materials)Acc: 0.589 -> 0.753Improved
train on DMS data instead of OpenSurfaces (same architecture)ResNet-50 dilated + PPM · Avg-Val (25 materials)mIoU: 0.416 -> 0.500Improved
train on DMS data instead of OpenSurfaces (same architecture)ResNet-50 dilated + PPM · Cross-dataset gap Delta (25 materials)Acc delta between datasets: 0.231 -> 0.047Improved
train on DMS data instead of OpenSurfaces (same architecture)ResNet-50 dilated + PPM · OS-Val (25 materials)mAcc: 0.702 -> 0.692Hurt
train on DMS data instead of OpenSurfacesResNet-50 dilated + PPM · DMS-Val photographic type: distant unreachable outdoor thingsper-pixel accuracy: 0.225 -> 0.736Improved
train on DMS data instead of OpenSurfacesResNet-50 dilated + PPM · DMS-Val photographic type: a real surface without contextper-pixel accuracy: 0.348 -> 0.691Improved
balance skin types in training data (DMS instead of OpenSurfaces)skin recognition, ResNet-50 dilated + PPM · DMS-Val skin typesaccuracy gap across skin types: 13.3% -> 3%Improved
select images to increase the underrepresented skin groupDMS image selection · DMS skin type distributionratio of largest to smallest skin group: 9.4 -> 2.2Improved
select images by photographic type to grow outdoor coverageDMS image selection · DMS outdoor material countsoccurrences of outdoor materials: growing the dataset by 17% more than doubled 9 kinds of outdoor materialsImproved
drop six rare classes (52 -> 46 materials)DMS-52 · DMS-ValmIoU: 0.392 -> 0.435Improved
add OpenSurfaces as extra training data to DMS-52DMS-52 · DMS-Val (52 materials)worst classesNo 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