Based on the MIL source code [1][2] and the paper[3], I think it shoudl be "variance" (or sigma squared) instead of "sigma". @challgrimson, what do you think?    --- [1] SIMILE: https://github.com/NanoscopyAI/SiMiLe-M/blob/e3e10efc7a1dba578c1ec8a07657dff8c541d403/CHWOS/SIMILE/model.py#L41 [2] lib MIL: https://github.com/NanoscopyAI/SiMiLe-M/blob/e3e10efc7a1dba578c1ec8a07657dff8c541d403/CHWOS/mil/models/bag_level/miles.py#L20 [3] MILES paper: http://infolab.stanford.edu/~wangz/project/imsearch/SVM/PAMI06/chen.pdf
Based on the MIL source code [1][2] and the paper[3], I think it shoudl be "variance" (or sigma squared) instead of "sigma".
@challgrimson, what do you think?
[1] SIMILE: https://github.com/NanoscopyAI/SiMiLe-M/blob/e3e10efc7a1dba578c1ec8a07657dff8c541d403/CHWOS/SIMILE/model.py#L41
[2] lib MIL: https://github.com/NanoscopyAI/SiMiLe-M/blob/e3e10efc7a1dba578c1ec8a07657dff8c541d403/CHWOS/mil/models/bag_level/miles.py#L20
[3] MILES paper: http://infolab.stanford.edu/~wangz/project/imsearch/SVM/PAMI06/chen.pdf