Closed philferriere closed 6 years ago
Thanks for your interest! These values were obtained with the balancing strategy explained in the article https://arxiv.org/pdf/1711.11069.pdf in the section Loss objective. We tried several balancing strategies and this is the one that worked best for us.
Thank you for taking the time to answer my questions, Miriam.
May I suggest that you perhaps make it more obvious in the paper over which dataset (or portion of the dataset) the class weighting terms were computed?
Re: "we tried several balancing strategies and this is the one that worked best for us." Could you quantify how much your dice score improved by using dataset-wide class weights instead of using the original per-image actual proportions, as used in the original implementation?
If you want to find the exact numbers of the comparison, they are in my Master thesis, in the section of Loss objective, there is a subsection of the different balancing techniques we used, and in the results section you can see the exact number (in Table 4.2). We used a validation set that we selected from the whole training volume of LiTS, in the thesis document there is also this information. We chose the first 80% volumes for training, and the remaining 20% for validation.
Thank you for the link and taking the time to address my questions, Miriam.
First, thank you for sharing your code with us. This is interesting work and I can't wait trying to reproduce some of your results.
I noticed that the way class-balanced cross entropy losses are computed here are slightly different from the "base" OSVOS implementation shared here where it is coded as follows:
However, for the lesion segmenter, the final loss is computed as shown here:
For the liver segmenter, it is computed using the following formula:
My questions are the following:
1/ Why use hardcoded constants instead of calculating the actual foreground/background proportions, as in the original implementation? 2/ What procedure did you use to come up with the hardcoded constants? Are those average foreground/background proportions over the entire training set? A portion of the training set? The training + validation set?
Thank you for your help with this!