IVCVLGJun 11, 2021

KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation

arXiv:2106.06237v3
AI Analysis

This addresses a more realistic and challenging problem in semantic segmentation for applications like medical imaging, though it is incremental as it builds on existing domain adaptation methods.

The paper tackles open-set domain adaptation in semantic segmentation, where test images may contain unknown categories and differ in distribution from labeled training images, by proposing KRADA to identify unknown-class pixels and align known-class distributions, achieving improved performance on synthetic and COVID-19 segmentation tasks.

In semantic segmentation, we aim to train a pixel-level classifier to assign category labels to all pixels in an image, where labeled training images and unlabeled test images are from the same distribution and share the same label set. However, in an open world, the unlabeled test images probably contain unknown categories and have different distributions from the labeled images. Hence, in this paper, we consider a new, more realistic, and more challenging problem setting where the pixel-level classifier has to be trained with labeled images and unlabeled open-world images -- we name it open-set domain adaptation segmentation (OSDAS). In OSDAS, the trained classifier is expected to identify unknown-class pixels and classify known-class pixels well. To solve OSDAS, we first investigate which distribution that unknown-class pixels obey. Then, motivated by the goodness-of-fit test, we use statistical measurements to show how a pixel fits the distribution of an unknown class and select highly-fitted pixels to form the unknown region in each test image. Eventually, we propose an end-to-end learning framework, known-region-aware domain alignment (KRADA), to distinguish unknown classes while aligning the distributions of known classes in labeled and unlabeled open-world images. The effectiveness of KRADA has been verified on two synthetic tasks and one COVID-19 segmentation task.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes