Search Results for author:
Found 8 papers, 5 papers with code
Counting Network for Learning from Majority Label
Existing MIL methods are unsuitable for LML due to aggregating confidences, which may lead to inconsistency between the bag-level label and the label obtained by counting the number of instances for each class.
Boosting for Bounding the Worst-class Error
This paper tackles the problem of the worst-class error rate, instead of the standard error rate averaged over all classes.
Deep Attentive Time Warping
Unlike other learnable models using DTW for warping, our model predicts all local correspondences between two time series and is trained based on metric learning, which enables it to learn the optimal data-dependent warping for the target task.
MixBag: Bag-Level Data Augmentation for Learning from Label Proportions
In this paper, we propose a bag-level data augmentation method for LLP called MixBag, based on the key observation from our preliminary experiments; that the instance-level classification accuracy improves as the number of labeled bags increases even though the total number of instances is fixed.
Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimization
This paper proposes a novel and efficient method for Learning from Label Proportions (LLP), whose goal is to train a classifier only by using the class label proportions of instance sets, called bags.
Dynamic Data Augmentation with Gating Networks for Time Series Recognition
We propose a neural network that dynamically selects the best combination of data augmentation methods using a mutually beneficial gating network and a feature consistency loss.
Attention to Warp: Deep Metric Learning for Multivariate Time Series
This approach adapts a parameterized attention model to time warping for greater and more adaptive temporal invariance.
Self-Augmented Multi-Modal Feature Embedding
To exploit this fact, we propose the use of self-augmentation and combine it with multi-modal feature embedding.
