About variance Lambda

[hmcoo]

In the page 4, it mentioned that The variance Λ_j is estimated using the feature vectors whose winner is j.

Can you elaborate the meaning of the winner? Did you define the winner for variance via:

1. a distribution of a feature vector which has a same label c_j?
2. you set the certain distance value as a metric, and choose the cetroids if their distances of other centroids are below (which means closer to a centroid) to the metric. And you get a variance from distribution among those centroids?
3. you set the certain integer as a metric, and get a list of centroids which index value equals to that metric. And you get a variance from the distribution from that centroids of that list?

Thank you for reading it and and stay safe.

[xyutao]

Given an input feature vector, the 'winner' is the ng node that matches that input (i.e., whose centroid vector has the minimum Euclidean distance to the input vector. Refer to the supplementary material.) Thus each node j corresponds to a set of feature vectors who are closer to j than other nodes. The variances of node j are computed using these feature vectors.

[hmcoo]

Given an input feature vector, the 'winner' is the ng node that matches that input (i.e., whose centroid vector has the minimum Euclidean distance to the input vector. Refer to the supplementary material.) Thus each node j corresponds to a set of feature vectors who are closer to j than other nodes. The variances of node j are computed using these feature vectors.

Thank you for quick reply.

Can I have one more question? During you calculate the anchor loss, you have used the variance. Do you have a special reason to use variance rather than covariance?

Thank you again, and have a good day.