Boosting Deep Unsupervised Edge Detection via Segment Anything Model | IEEE Journals & Magazine | IEEE Xplore

Boosting Deep Unsupervised Edge Detection via Segment Anything Model


Abstract:

Segment anything model (SAM), a vision foundation network trained on a massive segmentation corpus, exhibits a superior boundary localization capability for nature images...Show More

Abstract:

Segment anything model (SAM), a vision foundation network trained on a massive segmentation corpus, exhibits a superior boundary localization capability for nature images. This work aims to leverage such strengths to develop a deep unsupervised edge detection (UED) framework for alleviating the high reliance on dense labeling. However, applying vanilla SAM to edge detection fails to identify the salient edge cues but only the semantic boundary. This article introduces a lightweight adapter-tuning scheme to learn detailed edge information for filling the gap between boundary and edge, enabling a well-fitting even with limited training data. Moreover, considering the low-quality pseudo labels used in our UED framework, we propose two training strategies, adaptive progressive learning and gradient-guided pseudo label updating, to alleviate the impact of noisy labels from traditional UED methods. Extensive experiments demonstrate that our method achieves comparable results to state-of-the-art fully supervised edge detectors.
Published in: IEEE Transactions on Industrial Informatics ( Volume: 20, Issue: 6, June 2024)
Page(s): 8961 - 8971
Date of Publication: 03 April 2024

ISSN Information:

Funding Agency:


References

References is not available for this document.