no code implementations • 25 Oct 2023 • Zhimin Li, Shusen Liu, Kailkhura Bhavya, Timo Bremer, Valerio Pascucci
For a neural network model, the non-linear behavior is often caused by non-linear activation units of a model.
no code implementations • NeurIPS 2020 • Bhavya Kailkhura, Jayaraman J. Thiagarajan, Qunwei Li, Jize Zhang, Yi Zhou, Timo Bremer
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.
no code implementations • 16 Dec 2019 • Rushil Anirudh, Jayaraman J. Thiagarajan, Bhavya Kailkhura, Timo Bremer
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.
no code implementations • 20 Nov 2018 • Rushil Anirudh, Jayaraman J. Thiagarajan, Bhavya Kailkhura, Timo Bremer
Solving inverse problems continues to be a central challenge in computer vision.
no code implementations • 18 May 2018 • Rushil Anirudh, Jayaraman J. Thiagarajan, Bhavya Kailkhura, Timo Bremer
We solve this by making successive estimates on the model and the solution in an iterative fashion.
no code implementations • CVPR 2018 • Rushil Anirudh, Hyojin Kim, Jayaraman J. Thiagarajan, K. Aditya Mohan, Kyle Champley, Timo Bremer
The classical techniques require measuring projections, called sinograms, from a full 180$^\circ$ view of the object.