Is it possible to increase the precision to 100%?

[Lele-Xie]

Hi~ Recently, I have read some paper of yours (OpenMix, FMFP) about MisD or OOD. I am curious about whether it is possible to increase the precision to 100% by sacrificing some recall rate after using some related confidence techniques.

[Impression2805]

Thanks for your interest in our papers. For a specific dataset/model, you can plot the Accuracy-Rejection curves (fig.7 in OpenMix paper) or the Risk-Coverage curves, and find the rejection rate where the corresponding accuracy is 100% (or the risk is 0). To achieve exact 100% accuracy, the rejection rate might be high, and this depends on the dataset and model.

[Lele-Xie]

Thanks for your kind reply. But my curiosity is can your methods help to achieve this goal (100% acc with sacrificing recall rate).

---Original--- From: @.> Date: Thu, Aug 10, 2023 21:16 PM To: @.>; Cc: @.@.>; Subject: Re: [Impression2805/Awesome-Failure-Detection] Is it possible toincrease the precision to 100%? (Issue #1)

Thanks for your interest in our papers. For a specific dataset/model, you can plot the Accuracy-Rejection curves (fig.7 in OpenMix paper) or the Risk-Coverage curves, and find the rejection rate where the corresponding accuracy is 100% (or the risk is 0). To achieve exact 100% accuracy, the rejection rate might be high, and this depends on the dataset and model.

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>

[YutingLi0606]

Hello~ Our recent work SURE：SUrvey REcipes for building reliable and robust deep networks(CVPR2024) also focus on Failure Prediction(MisD) task.