Benutzer: Gast  Login
Titel:

Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Darestani, Mohammad Zalbagi; Liu, Jiayu; Heckel, Reinhard
Abstract:
Deep learning based image reconstruction methods outperform traditional methods. However, neural networks suffer from a performance drop when applied to images from a different distribution than the training images. For example, a model trained for reconstructing knees in accelerated magnetic resonance imaging (MRI) does not reconstruct brains well, even though the same network trained on brains reconstructs brains perfectly well. Thus there is a distribution shift performance gap for a given ne...     »
Herausgeber:
Chaudhuri, Kamalika; Jegelka, Stefanie; Song, Le; Szepesvari, Csaba; Niu, Gang; Sabato, Sivan
Kongress- / Buchtitel:
Proceedings of the 39th International Conference on Machine Learning
Band / Teilband / Volume:
162
Verlag / Institution:
PMLR
Jahr:
2022
Monat:
17--23 Jul
Seiten:
4754--4776
Serientitel:
Proceedings of Machine Learning Research
WWW:
https://proceedings.mlr.press/v162/darestani22a.html
 BibTeX