English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Self-training has greatly facilitated domain adaptive semantic segmentation,which iteratively generates pseudo labels on unlabeled target data and retrainsthe network. However, realistic segmentation datasets are highly imbalanced,pseudo labels are typically biased to the majority classes and basically noisy,leading to an error-prone and suboptimal model. In this paper, we propose asimple region-based active learning approach for semantic segmentation under adomain shift, aiming to automatically query a small partition of image regionsto be labeled while maximizing segmentation performance. Our algorithm, RegionImpurity and Prediction Uncertainty (RIPU), introduces a new acquisitionstrategy characterizing the spatial adjacency of image regions along with theprediction confidence. We show that the proposed region-based selectionstrategy makes more efficient use of a limited budget than image-based orpoint-based counterparts. Further, we enforce local prediction consistencybetween a pixel and its nearest neighbors on a source image. Alongside, wedevelop a negative learning loss to make the features more discriminative.Extensive experiments demonstrate that our method only requires very fewannotations to almost reach the supervised performance and substantiallyoutperforms state-of-the-art methods. The code is available athttps://github.com/BIT-DA/RIPU.

Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation