Papers › Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic...

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

26 Aug 2019ICCV 2019 10arXiv:1908.09547archive 2025-07-28

Qing Lian, Fengmao Lv, Lixin Duan, Boqing Gong

We propose a new approach, called self-motivated pyramid curriculum domain adaptation (PyCDA), to facilitate the adaptation of semantic segmentation neural networks from synthetic source domains to real target domains. Our approach draws on an insight connecting two existing works: curriculum domain adaptation and self-training. Inspired by the former, PyCDA constructs a pyramid curriculum which contains various properties about the target domain. Those properties are mainly about the desired label distributions over the target domain images, image regions, and pixels. By enforcing the segmentation neural network to observe those properties, we can improve the network's generalization capability to the target domain. Motivated by the self-training, we infer this pyramid of properties by resorting to the semantic segmentation network itself. Unlike prior work, we do not need to maintain any additional models (e.g., logistic regression or discriminator networks) or to solve minmax problems which are often difficult to optimize. We report state-of-the-art results for the adaptation from both GTAV and SYNTHIA to Cityscapes, two popular settings in unsupervised domain adaptation for semantic segmentation.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lianqing11/pycda mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain Adaptation Segmentation Semantic Segmentation Synthetic-to-Real Translation Unsupervised Domain Adaptation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Domain Adaptation	SYNTHIA-to-Cityscapes	PyCDA (ResNet-101)	mIoU	46.7	#22 of 33	Archive leaderboard	report
Domain Adaptation	SYNTHIA-to-Cityscapes	PyCDA (VGG-16)	mIoU	35.9	#33 of 33	Archive leaderboard	report
Image-to-Image Translation	SYNTHIA-to-Cityscapes	PyCDA (ResNet-101)	mIoU (13 classes)	53.3	#14 of 28	Archive leaderboard	report
Synthetic-to-Real Translation	GTAV-to-Cityscapes Labels	PyCDA	mIoU	48	#54 of 73	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Global Average Pooling Kaiming Initialization Logistic Regression Max Pooling ReLU Residual Block Residual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections