AI Paper Atlas

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

Constructing Self-Motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach

Qing Lian, Fengmao Lv, Lixin Duan, Boqing Gong

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 222 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 pixel-square middle layers to top + bottom pyramid (ablation)PyCDA (ResNet-101) · GTAV to CityscapesmIoU (%): 46.2 -> 47.4Improved
add pixel pseudo labels (bottom) to top-layer label distribution (ablation)PyCDA (ResNet-101) · GTAV to CityscapesmIoU (%): 42.0 -> 46.2Improved
add image-level label distributions (top) to pixel pseudo labels (ablation)PyCDA (ResNet-101) · GTAV to CityscapesmIoU (%): 40.6 -> 46.2Improved
combine CDA with ST at pixel level instead of either alone (ablation)PyCDA (VGG-16) · GTAV to CityscapesmIoU (%): 28.1 -> 34.9Improved
replace superpixels with pixel squares (ablation)PyCDA (ResNet-101) · GTAV to CityscapesmIoU (%): 46.3 -> 46.3No clear effect
use pixel squares in the middle layer in addition to pixel labels instead of top + squares only (ablation)PyCDA (ResNet-101) · GTAV to CityscapesmIoU (%): 46.3 -> 47.4Improved
add pixel-square middle layers on SYNTHIA (ablation)PyCDA (ResNet-101) · SYNTHIA to CityscapesmIoU (%): 44.8 -> 46.7Improved
add pixel-square middle layers on SYNTHIA (ablation)PyCDA (VGG-16) · SYNTHIA to CityscapesmIoU (%): 35.1 -> 35.9Improved
apply PyCDA domain adaptation to source-only modelFCN8s VGG-16 · GTAV to CityscapesmIoU (%): 24.3 -> 37.2Improved
apply PyCDA domain adaptation to source-only modelPSP-Net ResNet-101 · SYNTHIA to CityscapesmIoU (%): 33.0 -> 46.7Improved
use 16x16 square middle layer instead of 4x4 and 8x8 squares (ablation)PyCDA (ResNet-101) · GTAV to CityscapesmIoU (%): 47.4 -> 47.5No clear effect
use very large 128x128 squares in the pyramid (ablation)PyCDA (ResNet-101) · GTAV to CityscapesmIoU (%): 47.5 -> 47.0Hurt

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