Related papers: Adaptive Mixing of Auxiliary Losses in Supervised …

Knowledge distillation with unlabeled examples is a powerful training paradigm for generating compact and lightweight student models in applications where the amount of labeled data is limited but one has access to a large pool of unlabeled…

The problem of learning from few labeled examples while using large amounts of unlabeled data has been approached by various semi-supervised methods. Although these methods can achieve superior performance, the models are often not…

Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any…

Active Learning (AL) and Semi-supervised Learning are two techniques that have been studied to reduce the high cost of deep learning by using a small amount of labeled data and a large amount of unlabeled data. To improve the accuracy of…

Sparse additive models have attracted much attention in high-dimensional data analysis due to their flexible representation and strong interpretability. However, most existing models are limited to single-level learning under the…

A weakly-supervised learning framework named as complementary-label learning has been proposed recently, where each sample is equipped with a single complementary label that denotes one of the classes the sample does not belong to. However,…

Adversarial robustness is a research area that has recently received a lot of attention in the quest for trustworthy artificial intelligence. However, recent works on adversarial robustness have focused on supervised learning where it is…

The objective of active learning (AL) is to train classification models with less number of labeled instances by selecting only the most informative instances for labeling. The AL algorithms designed for other data types such as images and…

Model-Agnostic Meta-Learning (MAML), a popular gradient-based meta-learning framework, assumes that the contribution of each task or instance to the meta-learner is equal. Hence, it fails to address the domain shift between base and novel…

Active learning (AL) combines data labeling and model training to minimize the labeling cost by prioritizing the selection of high value data that can best improve model performance. In pool-based active learning, accessible unlabeled data…

Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only…

Metric learning projects samples into an embedded space, where similarities and dissimilarities are quantified based on their learned representations. However, existing methods often rely on label-guided representation learning, where…

Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations. Unlike semi-supervised learning, one cannot select the most…

In the context of label-efficient learning on video data, the distillation method and the structural design of the teacher-student architecture have a significant impact on knowledge distillation. However, the relationship between these…

Distillation with unlabeled examples is a popular and powerful method for training deep neural networks in settings where the amount of labeled data is limited: A large ''teacher'' neural network is trained on the labeled data available,…

Auxiliary Learning (AL) is a form of multi-task learning in which a model trains on auxiliary tasks to boost performance on a primary objective. While AL has improved generalization across domains such as navigation, image classification,…

We consider a collaborative learning setting where the goal of each agent is to improve their own model by leveraging the expertise of collaborators, in addition to their own training data. To facilitate the exchange of expertise among…

The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e.g.…

Medical image classification is often challenging for two reasons: a lack of labelled examples due to expensive and time-consuming annotation protocols, and imbalanced class labels due to the relative scarcity of disease-positive…

Conventional Supervised Learning approaches focus on the mapping from input features to output labels. After training, the learnt models alone are adapted onto testing features to predict testing labels in isolation, with training data…