Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Johanna P. Müller

Johanna P. Müller
Alert button

Pay Attention: Accuracy Versus Interpretability Trade-off in Fine-tuned Diffusion Models


Mar 31, 2023
Mischa Dombrowski, Hadrien Reynaud, Johanna P. Müller, Matthew Baugh, Bernhard Kainz

Add code
Alert button

Figure 1 for Pay Attention: Accuracy Versus Interpretability Trade-off in Fine-tuned Diffusion Models
Figure 2 for Pay Attention: Accuracy Versus Interpretability Trade-off in Fine-tuned Diffusion Models
Figure 3 for Pay Attention: Accuracy Versus Interpretability Trade-off in Fine-tuned Diffusion Models
Figure 4 for Pay Attention: Accuracy Versus Interpretability Trade-off in Fine-tuned Diffusion Models

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Confidence-Aware and Self-Supervised Image Anomaly Localisation


Mar 23, 2023
Johanna P. Müller, Matthew Baugh, Jeremy Tan, Mischa Dombrowski, Bernhard Kainz

Add code
Alert button

Figure 1 for Confidence-Aware and Self-Supervised Image Anomaly Localisation
Figure 2 for Confidence-Aware and Self-Supervised Image Anomaly Localisation
Figure 3 for Confidence-Aware and Self-Supervised Image Anomaly Localisation
Figure 4 for Confidence-Aware and Self-Supervised Image Anomaly Localisation
* Under Review 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

nnOOD: A Framework for Benchmarking Self-supervised Anomaly Localisation Methods


Sep 02, 2022
Matthew Baugh, Jeremy Tan, Athanasios Vlontzos, Johanna P. Müller, Bernhard Kainz

Add code
Alert button

Figure 1 for nnOOD: A Framework for Benchmarking Self-supervised Anomaly Localisation Methods
Figure 2 for nnOOD: A Framework for Benchmarking Self-supervised Anomaly Localisation Methods
Figure 3 for nnOOD: A Framework for Benchmarking Self-supervised Anomaly Localisation Methods
* Accepted as Spotlight to UNSURE 2022, a workshop at MICCAI 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email