hierarchical_anomaly_detection icon indicating copy to clipboard operation
hierarchical_anomaly_detection copied to clipboard

Published 5 years ago • verified publisher icon boschresearch
→

Metadata

Implementation of the paper "Understanding anomaly detection with deep invertible networks through hierarchies of distributions and features" (NeurIPS 2020)

Results 1 hierarchical_anomaly_detection issues
Sort by recently updated
recently updated
newest added

Why compute the likelihood contributed by different scales in this way?

I have two questions about the likelihood part. Question 1: In graph.py, https://github.com/boschresearch/hierarchical_anomaly_detection/blob/ca2f1d84615c2ef140a74f4e1515352abff9e938/invglow/invertible/graph.py#L222 the logdet is divided by n_parts (usually 2). Why the logdet is divided by 2 at SelectNode?...

williacode avatar williacode

← Metadata

42
Stars
3
Forks
42
Watchers

Owner

verified publisher icon boschresearch

Metadata

Implementation of the paper "Understanding anomaly detection with deep invertible networks through hierarchies of distributions and features" (NeurIPS 2020)

Back