activity
20162020
most citedUnderstanding the (un)interpretability of natural image distributions using generative models

10 citations · 12 across the 3 of their papers we have counts for

collaborators

6 papers

cs.LG20202 cited

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…

cs.LG201910 cited

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…

cs.CV2018

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…

cs.LG2018

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…

cs.CV2016

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…

cs.CV2016

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…