Marco Rudolph

Improper Normalization for CFlow-AD

2

Hi! I would like to point out that the aggregation of the feature maps for CFlow-AD appears to be improper, since the relative weighting of the individual maps depends on...

Improper normalization of the scores?

9

In train.py, you normalize the scores according to: ``` test_map = [list() for p in pool_layers] for l, p in enumerate(pool_layers): test_norm = torch.tensor(test_dist[l], dtype=torch.double) # EHWx1 test_norm-= torch.max(test_norm) #...

Negative Log Sigmoid Log Likelihood Loss?

2

Hi Denis! According to your code, you use some "negative log sigmoid log likelihood loss": https://github.com/gudovskiy/cflow-ad/blob/4d6ec4719e836422c5253a68c1150ac172d8000d/train.py#L76 https://github.com/gudovskiy/cflow-ad/blob/4d6ec4719e836422c5253a68c1150ac172d8000d/train.py#L78 with https://github.com/gudovskiy/cflow-ad/blob/4d6ec4719e836422c5253a68c1150ac172d8000d/train.py#L18 What is the motivation behind using this kind of loss? Thanks...

Experimental Details for NTU dataset

2

Dear authors, I read your work about "Graph Embedded pose Clustering for Anomaly Detection" with great interest. Some questions came up for me about the experiments with the NTU dataset:...