Official PyTorch implementation of the paper “Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection”, open-set anomaly detection, few-shot anomaly detection.
Hello,
I read your paper and code. I run some tests and I must say I'm impressed with the results. Good work! Right now I would like to improve the performance. I understand the optimization techniques will differ from the nature of the problem. I also read your suggestions like using other loss function. However, I would like to try different approaches. Right now I'm just familiar with traditional optimization techniques for deep learning, such as Early Stopping, but I would like to try new suggestions. If the authors or any reader know potential methods to optimize DRA, please share this knowledge in this Issue. It'd be grateful.
Hello, I read your paper and code. I run some tests and I must say I'm impressed with the results. Good work! Right now I would like to improve the performance. I understand the optimization techniques will differ from the nature of the problem. I also read your suggestions like using other loss function. However, I would like to try different approaches. Right now I'm just familiar with traditional optimization techniques for deep learning, such as Early Stopping, but I would like to try new suggestions. If the authors or any reader know potential methods to optimize DRA, please share this knowledge in this Issue. It'd be grateful.