Related papers: Active Learning with Task-Driven Representations f…

Chemical representations derived from deep learning are emerging as a powerful tool in areas such as drug discovery and materials innovation. Currently, this methodology has three major limitations - the cost of representation generation,…

In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream. Hence many existing deep learning solutions suffer from a limited…

How can we find a general way to choose the most suitable samples for training a classifier? Even with very limited prior information? Active learning, which can be regarded as an iterative optimization procedure, plays a key role to…

Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. It is non-trivial to manually design a robot controller that combines these modalities which have very different characteristics.…

Data cleaning is often an important step to ensure that predictive models, such as regression and classification, are not affected by systematic errors such as inconsistent, out-of-date, or outlier data. Identifying dirty data is often a…

Training multimodal networks requires a vast amount of data due to their larger parameter space compared to unimodal networks. Active learning is a widely used technique for reducing data annotation costs by selecting only those samples…

Often, labeling large amount of data is challenging due to high labeling cost limiting the application domain of deep learning techniques. Active learning (AL) tackles this by querying the most informative samples to be annotated among…

Despite the recent advances in multi-task learning of dense prediction problems, most methods rely on expensive labelled datasets. In this paper, we present a label efficient approach and look at jointly learning of multiple dense…

Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numerous unlabeled images that exist on the Internet and in…

Active learning is a powerful method for training machine learning models with limited labeled data. One commonly used technique for active learning is BatchBALD, which uses Bayesian neural networks to find the most informative points to…

Semi-supervised learning (SSL) is an efficient framework that can train models with both labeled and unlabeled data, but may generate ambiguous and non-distinguishable representations when lacking adequate labeled samples. With…

Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL)…

We examine the influence of input data representations on learning complexity. For learning, we posit that each model implicitly uses a candidate model distribution for unexplained variations in the data, its noise model. If the model…

Masked autoencoders have become popular training paradigms for self-supervised visual representation learning. These models randomly mask a portion of the input and reconstruct the masked portion according to the target representations. In…

Active Learning (AL) aims to reduce the labeling burden by interactively selecting the most informative samples from a pool of unlabeled data. While there has been extensive research on improving AL query methods in recent years, some…

Self-supervised learning (SSL), as a newly emerging unsupervised representation learning paradigm, generally follows a two-stage learning pipeline: 1) learning invariant and discriminative representations with auto-annotation pretext(s),…

Active learning is a learning strategy whereby the machine learning algorithm actively identifies and labels data points to optimize its learning. This strategy is particularly effective in domains where an abundance of unlabeled data…

We are concerned with the question of how an agent can acquire its own representations from sensory data. We restrict our focus to learning representations for long-term planning, a class of problems that state-of-the-art learning methods…

Classification algorithms aim to predict an unknown label (e.g., a quality class) for a new instance (e.g., a product). Therefore, training samples (instances and labels) are used to deduct classification hypotheses. Often, it is relatively…

Deep predictive models rely on human supervision in the form of labeled training data. Obtaining large amounts of annotated training data can be expensive and time consuming, and this becomes a critical bottleneck while building such models…