AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation

M.Naseer Subhani, Mohsen Ali

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 73 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 focal loss to the scale-invariant self-training loss (ablation)LSE (VGG16-FCN8) · GTA5 to CityscapesmIoU: 36.4 -> 39.0Improved
add focal loss to the scale-invariant self-training loss (ablation)LSE (VGG16-FCN8) · SYNTHIA to Cityscapes (16 classes)mIoU: 38.2 -> 40.0Improved
add focal loss to the scale-invariant self-training loss (ablation)LSE (VGG16-FCN8) · SYNTHIA to Cityscapes (13 classes)mIoU*: 44.9 -> 47.0Improved
add focal loss to balance class selection across rounds (ablation)LSE · GTA5 to Cityscapesimages selected per classImproved
use scale-invariant self-generated examples with focal loss instead of PyCDAPyCDA (VGG16-FCN8) · SYNTHIA to Cityscapes (16 classes)mIoU: 35.9 -> 40.0Improved
use scale-invariant self-generated examples with focal loss instead of PyCDAPyCDA (VGG16-FCN8) · GTA5 to CityscapesmIoU: 37.2 -> 39.0Improved
use scale-invariant self-generated examples with focal loss instead of PyCDAPyCDA (ResNet101) · GTA5 to CityscapesmIoU: 47.4 -> 47.5No clear effect
use scale-invariant self-generated examples with focal loss instead of PyCDAPyCDA (ResNet101) · SYNTHIA to Cityscapes (16 classes)mIoU: 46.7 -> 42.6Hurt
use LSE + FL instead of PyCDA, gap to oraclePyCDA · GTA5 to Cityscapes performance gap (VGG16-FCN8)gap to oracle (%): -27.9 -> -21.3Improved

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