activity
20172022
most citedRobust Inference via Generative Classifiers for Handling Noisy Labels

60 citations · 115 across the 4 of their papers we have counts for

collaborators
Showing 2018 · stat.MLShow all

1 paper · 2 filters

stat.ML2018

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

Kimin Lee, Kibok Lee, Honglak Lee +1

Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in man…