Defect detection for wear debris based on few-shot contrastive learning

HIGHLIGHTS

  • who: Hang Li et al. from the School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China have published the article: Defect Detection for Wear Debris Based on Few-Shot Contrastive Learning, in the Journal: (JOURNAL)
  • what: The authors propose a object detection network learning and multi-scale feature fusion. Comprehensive experiments are conducted to assess each method fairly. Inspired by Meta-FasterRCNN , the authors design an alignment module that establishes soft correspondences between query features and support features. The authors propose Multi-Scale Fusion not only to avoid the selection . . .

     

    Logo ScioWire Beta black

    If you want to have access to all the content you need to log in!

    Thanks :)

    If you don't have an account, you can create one here.

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?