search

marco-rudolph / AST

This is the code to the WACV 2023 paper "Asymmetric Student-Teacher Networks for Industrial Anomaly Detection" by Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn and Bastian Wandt.
66 stars 11 forks source link

question about big picture of Anomaly Detection #22

Closed limaodaxia closed 5 months ago

limaodaxia commented 5 months ago

Hi, @marco-rudolph Good morning, I am back again. I would like to ask you some general questions As I know, there are several method for Anomaly detection, such as Image Reconstruction, Normalize flow, Student-Teacher Network and memory bank based (like Patchcore). The research in this field is flourishing and tends to be saturated. I want to compare Student-Teacher Networks with Memory bank based method. I think Student-Techear Network is more worth studying than memory banks, because when inference memory bank cost some memory and it will find some similar feature, so it will cost some time. On the contrary, Student-Teacher Network directly use feature distance and do not need memory bank, so it is more efficient , Do you think my opinion is correct?

Best Limao

marco-rudolph commented 5 months ago

Hi,

sorry, but this is not the right place for discussions like this. Nevertheless, I will answer it briefly.

It's hard to generally speak from better/worse methods as you may have different setups or requirements in reality - for example regarding inference time, hardness of the problem, dataset size, availability of GPUs... Depending on the implementation and device, a memory bank may be faster than a NN pass. If you would make some assumptions, your reasoning may still apply.

Best, Marco

limaodaxia commented 5 months ago

Thank you very much. I greatly appreciate it that you can reply. If you need some help, you can feel free to comment here and let me know.