.png){kind=icon}
Return
Class-conditional domain adaptation for semantic segmentation
.png){kind=icon}
OA
AI
DOI：10.1007/s41095-023-0362-4.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Semantic segmentation is an important sub-task for many applications. However, pixel-level ground-truth labeling is costly, and there is a tendency to overfit to training data, thereby limiting the generalization ability. Unsupervised domain adaptation can potentially address these problems by allowing systems trained on labelled datasets from the source domain (including less expensive synthetic domain) to be adapted to a novel target domain. The conventional approach involves automatic extraction and alignment of the representations of source and target domains globally. One limitation of this approach is that it tends to neglect the differences between classes: representations of certain classes can be more easily extracted and aligned between the source and target domains than others, limiting the adaptation over all classes. Here, we address this problem by introducing a Class-Conditional Domain Adaptation (CCDA) method. This incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and adaptation. Together, they measure the segmentation, shift the domain in a class-conditional manner, and equalize the loss over classes. Experimental results demonstrate that the performance of our CCDA method matches, and in some cases, surpasses that of state-of-the-art methods.
Keywords:
domain adaptation
generative adversarial networks
semantic segmentation
cityscapes
Journal
IF:
18.3
Papers:
316
Citations:
2.6K
Organization
View more organizations
Cited Papers
cDNA sequence, tissue-specific expression, and chromosomal mapping of the human slow-twitch skeletal muscle isoform of troponin I.png)
Genomics
GenomicsIF0
PREAI
ShareSaveShareSaveDeterminants of quality of life in patients with fibromyalgia: A structural equation modeling approachPLOS ONE
OAAI
PLOS ONEIF0
OAAIShareSaveGross primary production of Mediterranean watersheds: Using isotope mass balance approach to improve estimationsEcohydrologyOAAI
EcohydrologyIF0
OAAIShareSaveShareSaveIOT Based Smart Electric Pole2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA)
2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA)IF0
PREAI
ShareSaveShareSave View more