search

shyam671 / Mask2Anomaly-Unmasking-Anomalies-in-Road-Scene-Segmentation

[ICCV'23 Oral] Unmasking Anomalies in Road-Scene Segmentation
49 stars 9 forks source link

contrast loss question #8

Open zhouhuan-hust opened 9 months ago

zhouhuan-hust commented 9 months ago

Hello， Congratulations on a great job！I have a question. For contrast loss, both normal and abnormal l_N are negative. The paper says that under ideal circumstances, normal l_N is -1 and abnormal is 0. Why does the formula for contrast loss seem to be to make normal l_N as close to 0 as possible and abnormal as much as possible greater than m(that is, 0.75), that is, abnormal is also as close to 0 as possible? Thank you very much!

shiyi-mu commented 8 months ago

I also have the same confusion

bieyl commented 7 months ago

running issue ood_out = anomaly_scores[ood_mask] IndexError: too many indices for array: array is 4-dimensional, but 5 were indexed can instruct me?Thanks!