2. Concerns for robustness and uncertainty
• Robustness to Common Corruptions
• Robustness to Adversarial Perturbations
• Robustness to Label Corruptions
• Out-of-Distribution Detection
• Conclusion
3. Predict the relative
position of image
patches
Use Resulting representation to
improve object detection
Self supervision for learning without labelled data
18. Robustness to label
corrupution
• The Gold Loss Correction (GLC) is a semi-verified method for label
noise robustness in deep learning classifiers.
20. Ablation study with
Imagenet
• Self-attention is useful in one-class OOD detection, enabling
the network to more easily learn shape and compare regions
across the whole image.
22. Conclusion
• Rotation prediction can improve classifier robustness to common
corruptions, adversarial perturbations, and label corruptions
• Helpful OOD detection
• OOD detection with large image size (224*224)
• Self attention is of great value in learning global structure