AI Paper Atlas

Research map / Detection and segmentation / CNN features

Trapped in Texture Bias? A Large Scale Comparison of Deep Instance Segmentation

Johannes Theodoridis, Jessica Hofmann, Johannes Maucher, Andreas Schilling

ECCV 2022 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 5 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
use deeper backbones (R101 vs R50, Swin-S vs Swin-T) (ablation)instance segmentation frameworks with FPN neck · Stylized COCOrAPImproved
use Swin Transformer backbone instead of ResNet of similar complexity (ablation)Mask R-CNN / Cascade · Stylized COCOrAPImproved
deeper/Swin backbones on small objects (ablation)instance segmentation frameworks · Stylized COCOrAPsMixed
use FPN neck instead of alternatives (C4, DC5, DCN) (ablation)Mask R-CNN, Cascade, YOLO etc. · Stylized COCOrAPHurt
add deformable convolutions (DCN) to the neck (ablation)FPN models · Stylized COCOrAPImproved
use DC5 neck (ablation)models on small objects · Stylized ObjectsrAPsImproved
change pre-training (supervised vs self-supervised), schedule or augmentation (ablation)Mask R-CNN R50 · Stylized COCOrAPNo clear effect
random initialization with Large Scale Jittering instead of ImageNet pre-training (ablation)Mask R-CNN · Stylized COCOrAPImproved
restrict stylization to objects only instead of full image (ablation)average framework · Stylized Objects vs Stylized COCOrAP: 72 -> 47 vs 58 -> 18Improved
stylize background only (ablation)average framework · Stylized BackgroundrAPs: 63 -> 63Hurt
stylize background only on large objects (ablation)average framework · Stylized BackgroundrAPl: 96 -> 101No clear effect
use YOLACT++ framework instead of Mask R-CNN / Cascade / BMask / BCNet / DETR (ablation)ResNet-50 + FPN frameworks · Stylized COCOrAPImproved

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