Related papers: Metadata Archaeology: Unearthing Data Subsets by L…

Unsupervised outlier detection is attractive because it eliminates the need for labeled data. Moreover, forming multi-model ensembles can improve detection robustness. However, composing an ensemble without labeled data is challenging.…

In this paper, we delve into the critical aspect of dataset quality assessment in machine learning classification tasks. Leveraging a variety of nine distinct datasets, each crafted for classification tasks with varying complexity levels,…

Fine-grained classification remains a very challenging problem, because of the absence of well-labeled training data caused by the high cost of annotating a large number of fine-grained categories. In the extreme case, given a set of test…

Action recognition is so far mainly focusing on the problem of classification of hand selected preclipped actions and reaching impressive results in this field. But with the performance even ceiling on current datasets, it also appears that…

Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled. This paper introduces a new method to identify such samples and mitigate their impact when training neural…

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…

Real-world text classification tasks often require many labeled training examples that are expensive to obtain. Recent advancements in machine teaching, specifically the data programming paradigm, facilitate the creation of training data…

Unsupervised machine learning is the training of an artificial intelligence system using information that is neither classified nor labeled, with a view to modeling the underlying structure or distribution in a dataset. Since unsupervised…

As a subset of machine learning, meta-learning, or learning to learn, aims at improving the model's capabilities by employing prior knowledge and experience. A meta-learning paradigm can appropriately tackle the conventional challenges of…

Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP…

Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task. This approach encounters difficulty when transfer is not advantageous, for instance, when tasks are considerably…

Learning with noisy labels remains challenging because over-parameterized networks memorize corrupted supervision. Meta-learning-based sample reweighting mitigates this by using a small clean subset to guide training, yet its behavior and…

In modern supervised learning, there are a large number of tasks, but many of them are associated with only a small amount of labeled data. These include data from medical image processing and robotic interaction. Even though each…

Meta-learning is a popular framework for learning with limited data in which an algorithm is produced by training over multiple few-shot learning tasks. For classification problems, these tasks are typically constructed by sampling a small…

In multi-label classification, each example in a dataset may be annotated as belonging to one or more classes (or none of the classes). Example applications include image (or document) tagging where each possible tag either applies to a…

In modern multilabel classification problems, each data instance belongs to a small number of classes from a large set of classes. In other words, these problems involve learning very sparse binary label vectors. Moreover, in large-scale…

Deep learning technology has developed unprecedentedly in the last decade and has become the primary choice in many application domains. This progress is mainly attributed to a systematic collaboration in which rapidly growing computing…

We consider a novel data driven approach for designing learning algorithms that can effectively learn with only a small number of labeled examples. This is crucial for modern machine learning applications where labels are scarce or…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of…