Corpus ID: 233168595

Active learning using weakly supervised signals for quality inspection

@article{Cordier2021ActiveLU,
  title={Active learning using weakly supervised signals for quality inspection},
  author={Antoine Cordier and Deepan Das and Pierre Gutierrez},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.02973}
}
Because manufacturing processes evolve fast and production visual aspect can vary significantly on a daily basis, the ability to rapidly update machine vision based inspection systems is paramount. Unfortunately, supervised learning of convolutional neural networks requires a significant amount of annotated images in order to learn effectively from new data. Acknowledging the abundance of continuously generated images coming from the production line and the cost of their annotation, we… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 29 REFERENCES
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
Cost-Effective Active Learning for Deep Image Classification
WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
...
1
2
3
...