Deep Learning
Multimodal Generative Models for Scalable Weakly-Supervised Learning
Neural Information Processing Systems http://nips.cc/
RandomNormalizationAggregationfor AdversarialDefense
Traditionally, this transferability is always regarded as a critical threat to the defense against adversarial attacks, however, we argue that the network robustness can be significantly boosted by utilizing adversarial transferability from anewperspective.
Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data
The assumption that data are independently and identically distributed (IID) is staple in statistical machine learning. It suggests that a hypothesis selected by an algorithm, after observing several training samples, should perform effectively on test samples from the same unknown distribution.
5aad86aa2a3c00b70c71e19bc4780319-Paper-Conference.pdf
Behavior is shaped by various factors operating across different timescales.
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
Zhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer, Michael W. Mahoney
Neural Information Processing Systems http://nips.cc/
DenoiseRep: DenoisingModelfor RepresentationLearning
Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03,vehicleID),imageclassification(ImageNet,UB200,Oxford-Pet,Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements.