-
https://github.com/ellenzhuwang/VK_OOD/blob/f7af0f40f1b75e668b0591dfe979c214fae5d189/vkood/modules/vk_module.py#L295
Hello, I would like to ask if there is any problem with the GMM model.
Should it …
-
Hi Litian,
I change your code from
score_in = torch.sum(logits_sub/denominator_matrix[nn_idx], axis=1)/torch.norm(feat_log_val - train_mean , dim = 1)
scores_out_test = torch.sum(logits_sub/den…
-
Hi,
In the paper, it writes: "Without assuming such knowledge, we use the maximum softmax probabilities to score anomalies and show that models which are **pre-trained then tuned** provide superior…
-
Is the score calculated in advance?
-
https://virtual2023.aclweb.org/paper_P5688.html
-
https://arxiv.org/abs/2309.15048
https://github.com/linhaowei1/TPL
-
Hey @nikitadurasov! 👋
When using the Masksembles method, I want to make a distinction between the different types of uncertainty (model/epistemic, label/aleatoric, and distributional/dataset shift…
-
- 논문에서 얻은 인사이트 정리
- 코드로 구현하는 방법 정리
- 우리꺼에 어떻게 적용할 수 있을지..? 생각하기
-
你好,
请问BrowserUpdate.exe这个文件是没有在仓库中提供吗？只有在/templates/thedataset/中有这个文件，在detection，discovery文件夹中并没有找到。
谢谢！
-
WWW
As a machine learning engineer looking for efficient solutions to out of domain detection, I would like to understand research and state of the art in this field.
- A recent paper called Is fine…