相关论文: Optimizing Multi-Domain Performance with Active Le…

Active learning aims to optimize the dataset annotation process when resources are constrained. Most existing methods are designed for balanced datasets. Their practical applicability is limited by the fact that a majority of real-life…

Autonomous driving algorithms rely heavily on learning-based models, which require large datasets for training. However, there is often a large amount of redundant information in these datasets, while collecting and processing these…

An active learner is given a class of models, a large set of unlabeled examples, and the ability to interactively query labels of a subset of these examples; the goal of the learner is to learn a model in the class that fits the data well.…

Much recent work on visual recognition aims to scale up learning to massive, noisily-annotated datasets. We address the problem of scaling- up the evaluation of such models to large-scale datasets with noisy labels. Current protocols for…

In many applications the process of generating label information is expensive and time consuming. We present a new method that combines active and semi-supervised deep learning to achieve high generalization performance from a deep…

Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from…

Active learning strategies respond to the costly labelling task in a supervised classification by selecting the most useful unlabelled examples in training a predictive model. Many conventional active learning algorithms focus on refining…

With the rising complexity of numerous novel applications that serve our modern society comes the strong need to design efficient computing platforms. Designing efficient hardware is, however, a complex multi-objective problem that deals…

Active learning has emerged as a standard paradigm in areas with scarcity of labeled training data, such as in the medical domain. Language models have emerged as the prevalent choice of several natural language tasks due to the performance…

In this work we present a general machine learning based scheme to optimize experimental control. The method utilizes the neural network to learn the relation between the control parameters and the control goal, with which the optimal…

Real world datasets contain incorrectly labeled instances that hamper the performance of the model and, in particular, the ability to generalize out of distribution. Also, each example might have different contribution towards learning.…

In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen data domain, e.g. a new centreor a new…

In many practical applications, it is often difficult and expensive to obtain large-scale labeled data to train state-of-the-art deep neural networks. Therefore, transferring the learned knowledge from a separate, labeled source domain to…

One of the important measures of quality of education is the performance of students in the academic settings. Nowadays, abundant data is stored in educational institutions about students which can help to discover insight on how students…

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…

The availability of labelled data is one of the main limitations in machine learning. We can alleviate this using weak supervision: a framework that uses expert-defined rules $\boldsymbol{\lambda}$ to estimate probabilistic labels…

Deep learning approaches are highly specialized and require training separate models for different tasks. Multi-domain learning looks at ways to learn a multitude of different tasks, each coming from a different domain, at once. The most…

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly.…

Competitive methods for multi-label classification typically invest in learning labels together. To do so in a beneficial way, analysis of label dependence is often seen as a fundamental step, separate and prior to constructing a…

Often the development of novel functional peptides is not amenable to high throughput or purely computational screening methods. Peptides must be synthesized one at a time in a process that does not generate large amounts of data. One way…