Deep Learning
Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
Work done while with Baidu Research.
Unsupervised learning of object structure and dynamics from videos
Matthias Minderer, Chen Sun, Ruben Villegas, Forrester Cole, Kevin P. Murphy, Honglak Lee
Neural Information Processing Systems http://nips.cc/
Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians
Axel Brando, Jose A. Rodriguez, Jordi Vitria, Alberto Rubio Muรฑoz
On the other hand, another source of uncertainty is "inevitable variability in the response variable", i.e. when the variable to predict exhibits randomness,
Adaptive Cross-Modal Few-shot Learning
Chen Xing, Negar Rostamzadeh, Boris Oreshkin, Pedro O. O. Pinheiro
Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition.
Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
Aditya Grover, Jiaming Song, Ashish Kapoor, Kenneth Tran, Alekh Agarwal, Eric J. Horvitz, Stefano Ermon
A learned generative model often produces biased statistics relative to the underlying data distribution.
Geometry-Informed Neural Operator for Large-Scale 3D PDEs
To empirically validate the performance of our method on large-scale simulation, we generate the industry-standard aerodynamics dataset of 3D vehicle geometries with Reynolds numbers as high as five million. For this large-scale 3D fluid simulation, numerical methods are expensive to compute surface pressure.
Recurrent Kernel Networks
Substring kernels are classical tools for representing biological sequences or text.
Sim2real transfer learning for 3D human pose estimation: motion to the rescue
Carl Doersch, Andrew Zisserman
Neural Information Processing Systems http://nips.cc/
Co-Generation with GANs using AIS based HMC
Tiantian Fang, Alexander Schwing
Therefore, in this paper, we study the occurring challenges for co-generation with GANs. To address those challenges we develop an annealed importance sampling based Hamiltonian Monte Carlo co-generation algorithm.
