Saliency is a Possible Red Herring When Diagnosing Poor Generalization
暂无分享,去创建一个
Yoshua Bengio | Joseph Paul Cohen | Francis Dutil | Joseph D. Viviano | Becks Simpson | Yoshua Bengio | Francis Dutil | J. Viviano | B. Simpson
[1] Leslie G. Valiant,et al. A theory of the learnable , 1984, STOC '84.
[2] Charu C. Aggarwal,et al. On the Surprising Behavior of Distance Metrics in High Dimensional Spaces , 2001, ICDT.
[3] Sébastien Marcel,et al. Torchvision the machine-vision package of torch , 2010, ACM Multimedia.
[4] Francisco Herrera,et al. A unifying view on dataset shift in classification , 2012, Pattern Recognit..
[5] Brian C. Lovell,et al. Unsupervised Domain Adaptation by Domain Invariant Projection , 2013, 2013 IEEE International Conference on Computer Vision.
[6] Rob Fergus,et al. Visualizing and Understanding Convolutional Networks , 2013, ECCV.
[7] Barbara Hammer,et al. Neural Smithing – Supervised Learning in Feedforward Artificial Neural Networks , 2001, Pattern Analysis & Applications.
[8] Yoshua Bengio,et al. Generative Adversarial Nets , 2014, NIPS.
[9] Andrew Zisserman,et al. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.
[10] Victor S. Lempitsky,et al. Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.
[11] Joseph Paul Cohen,et al. Prediction gradients for feature extraction and analysis from convolutional neural networks , 2015, 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG).
[12] Trevor Darrell,et al. Simultaneous Deep Transfer Across Domains and Tasks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).
[13] Jimmy Ba,et al. Adam: A Method for Stochastic Optimization , 2014, ICLR.
[14] Leon A. Gatys,et al. A Neural Algorithm of Artistic Style , 2015, ArXiv.
[15] Jian Sun,et al. Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[16] Ming-Yu Liu,et al. Coupled Generative Adversarial Networks , 2016, NIPS.
[17] Guigang Zhang,et al. Deep Learning , 2016, Int. J. Semantic Comput..
[18] Mehrtash Tafazzoli Harandi,et al. Distribution-Matching Embedding for Visual Domain Adaptation , 2016, J. Mach. Learn. Res..
[19] Ronald M. Summers,et al. ChestX-ray: Hospital-Scale Chest X-ray Database and Benchmarks on Weakly Supervised Classification and Localization of Common Thorax Diseases , 2019, Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics.
[20] Trevor Darrell,et al. Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[21] Yoshua Bengio,et al. Measuring the tendency of CNNs to Learn Surface Statistical Regularities , 2017, ArXiv.
[22] Samy Bengio,et al. Understanding deep learning requires rethinking generalization , 2016, ICLR.
[23] Andrew Slavin Ross,et al. Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations , 2017, IJCAI.
[24] Graham W. Taylor,et al. Improved Regularization of Convolutional Neural Networks with Cutout , 2017, ArXiv.
[25] Ankur Taly,et al. Axiomatic Attribution for Deep Networks , 2017, ICML.
[26] Cengiz Öztireli,et al. Towards better understanding of gradient-based attribution methods for Deep Neural Networks , 2017, ICLR.
[27] Marcus A. Badgeley,et al. Confounding variables can degrade generalization performance of radiological deep learning models , 2018, ArXiv.
[28] Marcus A. Badgeley,et al. Deep learning predicts hip fracture using confounding patient and healthcare variables , 2018, npj Digital Medicine.
[29] Sally Shrapnel,et al. Deep neural network or dermatologist? , 2019, iMIMIC/ML-CDS@MICCAI.
[30] F. Pfeiffer,et al. Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and Visualization , 2019, Scientific Reports.
[31] Carol C Wu,et al. Augmenting the National Institutes of Health Chest Radiograph Dataset with Expert Annotations of Possible Pneumonia. , 2019, Radiology. Artificial intelligence.
[32] Beomsu Kim,et al. Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).
[33] Yoshua Bengio,et al. GradMask: Reduce Overfitting by Regularizing Saliency , 2019, ArXiv.
[34] Pascal Sturmfels,et al. Learning Explainable Models Using Attribution Priors , 2019, ArXiv.
[35] Jianguo Zhang,et al. CARE: Class Attention to Regions of Lesion for Classification on Imbalanced Data , 2019, MIDL.
[36] Andrew Kyle Lampinen,et al. What shapes feature representations? Exploring datasets, architectures, and training , 2020, NeurIPS.
[37] M. Bethge,et al. Shortcut learning in deep neural networks , 2020, Nature Machine Intelligence.
[38] Joseph Paul Cohen,et al. On the limits of cross-domain generalization in automated X-ray prediction , 2020, MIDL.
[39] Chandan Singh,et al. Interpretations are useful: penalizing explanations to align neural networks with prior knowledge , 2019, ICML.
[40] Gabriel Erion,et al. An adversarial approach for the robust classification of pneumonia from chest radiographs , 2020, CHIL.
[41] Joseph D. Janizek,et al. AI for radiographic COVID-19 detection selects shortcuts over signal , 2020, Nature Machine Intelligence.
[42] Alexander D'Amour,et al. Underspecification Presents Challenges for Credibility in Modern Machine Learning , 2020, J. Mach. Learn. Res..
[43] Bilal Alsallakh,et al. Captum: A unified and generic model interpretability library for PyTorch , 2020, ArXiv.
[44] John Paoli,et al. Human–computer collaboration for skin cancer recognition , 2020, Nature Medicine.
[45] Antonio Pertusa,et al. PadChest: A large chest x-ray image dataset with multi-label annotated reports , 2019, Medical Image Anal..
[46] Wouter M. Kouw,et al. A Review of Domain Adaptation without Target Labels , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.
[47] B. Schölkopf,et al. Learning explanations that are hard to vary , 2020, ICLR.
[48] Joseph Paul Cohen,et al. TorchXRayVision: A library of chest X-ray datasets and models , 2021, MIDL.