55 citations · 109 across the 7 of their papers we have counts for
9 papers
Conformation Generation using Transformer Flows
Sohil Atul Shah, Vladlen Koltun
Estimating three-dimensional conformations of a molecular graph allows insight into the molecule's biological and chemical functions. Fast generation of valid conformations is thus…
Auto-decoding Graphs
Sohil Atul Shah, Vladlen Koltun
We present an approach to synthesizing new graph structures from empirically specified distributions. The generative model is an auto-decoder that learns to synthesize graphs from…
Understanding the (un)interpretability of natural image distributions using generative models
Ryen Krusinga, Sohil Shah, Matthias Zwicker +2
Probability density estimation is a classical and well studied problem, but standard density estimation methods have historically lacked the power to model complex and high-dimensi…
Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation
Sohil Shah, Pallabi Ghosh, Larry S Davis +1
Many imaging tasks require global information about all pixels in an image. Conventional bottom-up classification networks globalize information by decreasing resolution; features…
Deep Continuous Clustering
Sohil Atul Shah, Vladlen Koltun
Clustering high-dimensional datasets is hard because interpoint distances become less informative in high-dimensional spaces. We present a clustering algorithm that performs nonlin…
Stabilizing Adversarial Nets With Prediction Methods
Abhay Yadav, Sohil Shah, Zheng Xu +2
Adversarial neural networks solve many important problems in data science, but are notoriously difficult to train. These difficulties come from the fact that optimal weights for ad…
Weakly Supervised Learning of Heterogeneous Concepts in Videos
Sohil Shah, Kuldeep Kulkarni, Arijit Biswas +3
Typical textual descriptions that accompany online videos are 'weak': i.e., they mention the main concepts in the video but not their corresponding spatio-temporal locations. The c…
Estimating Sparse Signals with Smooth Support via Convex Programming and Block Sparsity
Sohil Shah, Tom Goldstein, Christoph Studer
Conventional algorithms for sparse signal recovery and sparse representation rely on -norm regularized variational methods. However, when applied to the reconstruction of $\te…
Biconvex Relaxation for Semidefinite Programming in Computer Vision
Sohil Shah, Abhay Kumar, Carlos Castillo +3
Semidefinite programming is an indispensable tool in computer vision, but general-purpose solvers for semidefinite programs are often too slow and memory intensive for large-scale…