You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi,
This is more of a theoretical query. Is there a way to make sure all embeddings in the queue(maintained in the MoCo v2 training mechanism) are actually negative samples?
e.g., there is a possibility that one or more embeddings in the queue are actually positive examples with respect to the current key/query.
Has this been handled in MaskContrast, or could you point to any work on the same?
Thanks.
The text was updated successfully, but these errors were encountered:
silky1708
changed the title
possibility of negative samples/embeddings in MoCo queue
possibility of positive samples/embeddings in MoCo queue
Oct 25, 2022
Hi,
This is more of a theoretical query. Is there a way to make sure all embeddings in the queue(maintained in the MoCo v2 training mechanism) are actually negative samples?
e.g., there is a possibility that one or more embeddings in the queue are actually positive examples with respect to the current key/query.
Has this been handled in MaskContrast, or could you point to any work on the same?
Thanks.
The text was updated successfully, but these errors were encountered: