4 papers
The Urban Vision Hackathon Dataset and Models: Towards Image Annotations and Accurate Vision Models for Indian Traffic
Akash Sharma, Chinmay Mhatre, Sankalp Gawali +10
This report describes the UVH-26 dataset, the first public release by AIM@IISc of a large-scale dataset of annotated traffic-camera images from India. The dataset comprises 26,646…
Score-based constrained generative modeling via Langevin diffusions with boundary conditions
Adam Nordenhög, Akash Sharma
Score-based generative models based on stochastic differential equations (SDEs) achieve impressive performance in sampling from unknown distributions, but often fail to satisfy und…
Weak approximation of stochastic differential equations with sticky boundary conditions
Akash Sharma
Sticky diffusion models a Markovian particle experiencing reflection and temporary adhesion phenomena at the boundary. Numerous numerical schemes exist for approximating stopped or…
Sampling and estimation on manifolds using the Langevin diffusion
Karthik Bharath, Alexander Lewis, Akash Sharma +1
Error bounds are derived for sampling and estimation using a discretization of an intrinsically defined Langevin diffusion with invariant measure $\text{d}μ_Ï\propto e^{-Ï} \mat…