For an historian, the first step in studying their evolution in a corpus of similar manuscripts is to identify which ones correspond to each other.
On Clothing1M, our approach obtains 74. 9% accuracy which is slightly better than that of DivideMix.
Ranked #1 on Learning with noisy labels on ANIMAL
The evidence lower bound of the marginal log-likelihood of empirical Bayes decomposes as a sum of local KL divergences between the variational posterior and the true posterior on the query set of each task.
Historical watermark recognition is a highly practical, yet unsolved challenge for archivists and historians.
The MAAN employs a novel marginalized average aggregation (MAA) module and learns a set of latent discriminative probabilities in an end-to-end fashion.
Our goal in this paper is to discover near duplicate patterns in large collections of artworks.