Transfusion: Understanding Transfer Learning with Applications to Medical ImagingEI
With the increasingly varied applications of deep learning, transfer learning has emerged as a critically important technique. However, the central question of how much feature reuse in transfer is the source of benefit remains unanswered. In this paper, we present an in-depth analysis of the effects of transfer, focusing on medical imaging, which is a particularly intriguing setting. Here, transfer learning is extremely popular, but data differences between pretraining and finetuing are considerable, reiterating the question of what ...更多
- 2Sergey Ioffe, Christian Szegedy. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.International Conference on Machine Learning, 2015.
- 3Aravindh Mahendran, Andrea Vedaldi. Understanding deep image representations by inverting them.CVPR, pp. 5188-5196, 2015.
- 4Ahsan Haseeb, Diabetic retinopathy--biomolecules and multiple pathophysiology.Diabetes & metabolic syndrome, pp. 51-54, 2015.
- 5Jason Yosinski, Jeff Clune, Yoshua Bengio, Hod Lipson. How transferable are features in deep neural networks?.NIPS, pp. 3320-3328, 2014.
- 7Dayong Wang, Aditya Khosla, Rishab Gargeya, Humayun Irshad, Andrew H. Beck. Deep Learning for Identifying Metastatic Breast Cancer.CoRR, 2016.
- 9Yun Liu, Krishna Gadepalli, Mohammad Norouzi, George E. Dahl, Timo Kohlberger, Aleksey Boyko, Subhashini Venugopalan, Aleksei Timofeev, Philip Q. Nelson, Gregory S. Corrado, Jason D. Hipp, Lily Peng, Martin C. Stumpe. Detecting Cancer Metastases on Gigapixel Pathology Images.CoRR, 2017.
- 10Xiaosong Wang, Yifan Peng, Le Lu, Zhiyong Lu, Mohammadhadi Bagheri, Ronald M. Summers. ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases.CVPR, 2017.
- 11Maithra Raghu, Justin Gilmer, Jason Yosinski, Jascha Sohl-Dickstein. SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability.NIPS, pp. 6078-6087, 2017.
- 12Pranav Rajpurkar, Jeremy Irvin, Kaylie Zhu, Brandon Yang, Hershel Mehta, Tony Duan, Daisy Ding, Aarti Bagul, Curtis Langlotz, Katie Shpanskaya, Matthew P. Lungren, Andrew Y. Ng. CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning.CoRR, 2017.
- 15Ari S. Morcos, Maithra Raghu, Samy Bengio. Insights on representational similarity in neural networks with canonical correlation.NeurIPS, pp. 5727-5736, 2018.
- 16Maithra Raghu, Katy Blumer, Rory Sayres, Ziad Obermeyer, Sendhil Mullainathan, Jon M. Kleinberg. Direct Uncertainty Prediction with Applications to Healthcare.CoRR, 2018.
- 17Maithra Raghu, Katy Blumer, Rory Sayres, Ziad Obermeyer, Sendhil Mullainathan, Jon M. Kleinberg. Direct Uncertainty Prediction for Medical Second Opinions.arXiv: Learning, 2018.
- 18Jiquan Ngiam, Daiyi Peng, Vijay Vasudevan, Simon Kornblith, Quoc V. Le, Ruoming Pang. Domain Adaptive Transfer Learning with Specialist Models.CoRR, 2018.
- 19Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, Wieland Brendel. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness.CoRR, 2018.