Related papers: SeqMix: Augmenting Active Sequence Labeling via Se…
Data augmentation improves the generalization power of deep learning models by synthesizing more training samples. Sample-mixing is a popular data augmentation approach that creates additional data by combining existing samples. Recent…
The most competitive noisy label learning methods rely on an unsupervised classification of clean and noisy samples, where samples classified as noisy are re-labelled and "MixMatched" with the clean samples. These methods have two issues in…
Supervised classification algorithms are used to solve a growing number of real-life problems around the globe. Their performance is strictly connected with the quality of labels used in training. Unfortunately, acquiring good-quality…
Sketch recognition allows natural and efficient interaction in pen-based interfaces. A key obstacle to building accurate sketch recognizers has been the difficulty of creating large amounts of annotated training data. Several authors have…
Deep neural networks have reached high accuracy on object detection but their success hinges on large amounts of labeled data. To reduce the labels dependency, various active learning strategies have been proposed, typically based on the…
Deep learning research over the past years has shown that by increasing the scope or difficulty of the learning problem over time, increasingly complex learning problems can be addressed. We study incremental learning in the context of…
Human annotation of training samples is expensive, laborious, and sometimes challenging, especially for Natural Language Processing (NLP) tasks. To reduce the labeling cost and enhance the sample efficiency, Active Learning (AL) technique…
Techniques combining multiple images as input/output have proven to be effective data augmentations for training convolutional neural networks. In this paper, we present StackMix: Each input is presented as a concatenation of two images,…
Labeling time series data is an expensive task because of domain expertise and dynamic nature of the data. Hence, we often have to deal with limited labeled data settings. Data augmentation techniques have been successfully deployed in…
Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a…
In multiple instance multiple label learning, each sample, a bag, consists of multiple instances. To alleviate labeling complexity, each sample is associated with a set of bag-level labels leaving instances within the bag unlabeled. This…
We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained unlabelled data in order to scale up performance. Most existing semi-supervised methods rely on the assumption that…
In this paper, we investigate the challenges of complementary-label learning (CLL), a specialized form of weakly-supervised learning (WSL) where models are trained with labels indicating classes to which instances do not belong, rather than…
While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These techniques hold particular significance in industrial…
This paper proposes a simple yet effective interpolation-based data augmentation approach termed DoubleMix, to improve the robustness of models in text classification. DoubleMix first leverages a couple of simple augmentation operations to…
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…
Gathering training data is a key step of any supervised learning task, and it is both critical and expensive. Critical, because the quantity and quality of the training data has a high impact on the performance of the learned function.…
Data augmentation with \textbf{Mixup} has been proven an effective method to regularize the current deep neural networks. Mixup generates virtual samples and corresponding labels at once through linear interpolation. However, this one-stage…
State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance. While unlabelled data can be largely available and even abundant, annotation process can…
At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…