activity
20172026
most citedProbabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection

37 citations · 78 across the 15 of their papers we have counts for

collaborators
Showing stat.MLShow all

2 papers · 1 filter

stat.ML2019

Tree pyramidal adaptive importance sampling

Javier Felip, Nilesh Ahuja, Omesh Tickoo

This paper introduces Tree-Pyramidal Adaptive Importance Sampling (TP-AIS), a novel iterated sampling method that outperforms state-of-the-art approaches like deterministic mixture…

stat.ML2019★ 37 cited

Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection

Nilesh A. Ahuja, Ibrahima Ndiour, Trushant Kalyanpur +1

We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks. Our approach consists in modeling the outputs of the vario…