Search Results for author: Megh Shukla

Found 5 papers, 5 papers with code

TIC-TAC: A Framework To Learn And Evaluate Your Covariance

1 code implementation29 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 $x$.

Pose Estimation

Bayesian Uncertainty and Expected Gradient Length -- Regression: Two Sides Of The Same Coin?

3 code implementations19 Apr 2021 Megh Shukla

Subsequently, we show that expected gradient length in regression is equivalent to Bayesian uncertainty.

Active Learning Pose Estimation +1

A Mathematical Analysis of Learning Loss for Active Learning in Regression

1 code implementation19 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.

Active Learning Pose Estimation +1

LEt-SNE: A Hybrid Approach To Data Embedding and Visualization of Hyperspectral Imagery

2 code implementations19 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.

Clustering Dimensionality Reduction

Cannot find the paper you are looking for? You can Submit a new open access paper.