Related papers: Efficient Algorithms for Learning from Coarse Labe…

We measure the effect of small amounts of systematic and random label noise caused by slightly misaligned ground truth labels in a fine grained audio signal labeling task. The task we choose to demonstrate these effects on is also known as…

Fine-grained categorization can benefit from part-based features which reveal subtle visual differences between object categories. Handcrafted features have been widely used for part detection and classification. Although a recent trend…

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…

We propose techniques to incorporate coarse taxonomic labels to train image classifiers in fine-grained domains. Such labels can often be obtained with a smaller effort for fine-grained domains such as the natural world where categories are…

Noisy Labels are commonly present in data sets automatically collected from the internet, mislabeled by non-specialist annotators, or even specialists in a challenging task, such as in the medical field. Although deep learning models have…

We consider the problem of semantic image segmentation using deep convolutional neural networks. We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at…

Partial label learning deals with the problem where each training instance is assigned a set of candidate labels, only one of which is correct. This paper provides the first attempt to leverage the idea of self-training for dealing with…

Data lies at the core of modern deep learning. The impressive performance of supervised learning is built upon a base of massive accurately labeled data. However, in some real-world applications, accurate labeling might not be viable;…

We present a new perspective on the popular multi-class algorithmic techniques of one-vs-all and error correcting output codes. Rather than studying the behavior of these techniques for supervised learning, we establish a connection between…

Learning segmentation from noisy labels is an important task for medical image analysis due to the difficulty in acquiring highquality annotations. Most existing methods neglect the pixel correlation and structural prior in segmentation,…

Current approaches for fine-grained recognition do the following: First, recruit experts to annotate a dataset of images, optionally also collecting more structured data in the form of part annotations and bounding boxes. Second, train a…

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each…

Large scale image classification datasets often contain noisy labels. We take a principled probabilistic approach to modelling input-dependent, also known as heteroscedastic, label noise in these datasets. We place a multivariate Normal…

Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much…

Long-tailed learning has attracted much attention recently, with the goal of improving generalisation for tail classes. Most existing works use supervised learning without considering the prevailing noise in the training dataset. To move…

The recent success of deep learning is mostly due to the availability of big datasets with clean annotations. However, gathering a cleanly annotated dataset is not always feasible due to practical challenges. As a result, label noise is a…

The problem of devising learning strategies for discrete losses (e.g., multilabeling, ranking) is currently addressed with methods and theoretical analyses ad-hoc for each loss. In this paper we study a least-squares framework to…

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.…

Image classification problems are typically addressed by first collecting examples with candidate labels, second cleaning the candidate labels manually, and third training a deep neural network on the clean examples. The manual labeling…

A long-standing issue with deep learning is the need for large and consistently labeled datasets. Although the current research in semi-supervised learning can decrease the required amount of annotated data by a factor of 10 or even more,…