1 code implementation • 29 Oct 2023 • Megh Shukla, Mathieu Salzmann, Alexandre Alahi
We study the problem of unsupervised heteroscedastic covariance estimation, where the goal is to learn the multivariate target distribution $\mathcal{N}(y, \Sigma_y | x )$ given an observation $x$.
1 code implementation • 12 Oct 2022 • Megh Shukla, Roshan Roy, Pankaj Singh, Shuaib Ahmed, Alexandre Alahi
We begin with a simple premise: pose estimators often predict incoherent poses for out-of-distribution samples.
3 code implementations • 19 Apr 2021 • Megh Shukla
Subsequently, we show that expected gradient length in regression is equivalent to Bayesian uncertainty.
1 code implementation • 19 Apr 2021 • Megh Shukla, Shuaib Ahmed
We show that LearningLoss++ outperforms in identifying scenarios where the model is likely to perform poorly, which on model refinement translates into reliable performance in the open world.
2 code implementations • 19 Oct 2019 • Megh Shukla, Biplab Banerjee, Krishna Mohan Buddhiraju
Some popular techniques among these falter when applied to Hyperspectral Imagery due to the famed curse of dimensionality.