Search Results for author:
Found 6 papers, 0 papers with code
Instance-wise Linearization of Neural Network for Model Interpretation
For a neural network model, the non-linear behavior is often caused by non-linear activation units of a model.
A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning
Using this framework, we show that space-filling sample designs, such as blue noise and Poisson disk sampling, which optimize spectral properties, outperform random designs in terms of the generalization gap and characterize this gain in a closed-form.
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking
However, PGD is a brittle optimization technique that fails to identify the right projection (or latent vector) when the observation is corrupted, or perturbed even by a small amount.
MimicGAN: Corruption-Mimicking for Blind Image Recovery & Adversarial Defense
Solving inverse problems continues to be a central challenge in computer vision.
An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks
We solve this by making successive estimates on the model and the solution in an iterative fashion.
Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion
The classical techniques require measuring projections, called sinograms, from a full 180$^\circ$ view of the object.
