Search Results for author:
Found 5 papers, 1 papers with code
Weakly Supervised Regression with Interval Targets
Third, we propose a statistically consistent limiting method for RIT to train the model by limiting the predictions to the interval.
Generalized Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses
\emph{Classification with rejection} (CwR) refrains from making a prediction to avoid critical misclassification when encountering test samples that are difficult to classify.
Multi-Class Classification from Single-Class Data with Confidences
We show that without any assumptions on the loss functions, models, and optimizers, we can successfully learn a multi-class classifier from only data of a single class with a rigorous consistency guarantee when confidences (i. e., the class-posterior probabilities for all the classes) are available.
Learning from Similarity-Confidence Data
Weakly supervised learning has drawn considerable attention recently to reduce the expensive time and labor consumption of labeling massive data.
Multi-Complementary and Unlabeled Learning for Arbitrary Losses and Models
We first give an unbiased estimator of the classification risk from samples with multiple complementary labels, and then further improve the estimator by incorporating unlabeled samples into the risk formulation.
Ranked #20 on
Image Classification
on Kuzushiji-MNIST
