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

Deep learning has become a powerful tool for Mars exploration. Mars terrainsemantic segmentation is an important Martian vision task, which is the base ofrover autonomous planning and safe driving. However, there is a lack ofsufficient detailed and high-confidence data annotations, which are exactlyrequired by most deep learning methods to obtain a good model. To address thisproblem, we propose our solution from the perspective of joint data and methoddesign. We first present a newdataset S5Mars for Semi-SuperviSed learning onMars Semantic Segmentation, which contains 6K high-resolution images and issparsely annotated based on confidence, ensuring the high quality of labels.Then to learn from this sparse data, we propose a semi-supervised learning(SSL) framework for Mars image semantic segmentation, to learn representationsfrom limited labeled data. Different from the existing SSL methods which aremostly targeted at the Earth image data, our method takes into account Marsdata characteristics. Specifically, we first investigate the impact of currentwidely used natural image augmentations on Mars images. Based on the analysis,we then proposed two novel and effective augmentations for SSL of Marssegmentation, AugIN and SAM-Mix, which serve as strong augmentations to boostthe model performance. Meanwhile, to fully leverage the unlabeled data, weintroduce a soft-to-hard consistency learning strategy, learning from differenttargets based on prediction confidence. Experimental results show that ourmethod can outperform state-of-the-art SSL approaches remarkably. Our proposeddataset is available at https://jhang2020.github.io/S5Mars.github.io/.

S$^{5}$Mars: Semi-Supervised Learning for Mars Semantic Segmentation