Related papers: Towards Fairness under Label Bias in Image Segment…

Labeling bias arises during data collection due to resource limitations or unconscious bias, leading to unequal label error rates across subgroups or misrepresentation of subgroup prevalence. Most fairness constraints assume training labels…

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…

A person downloading a pre-trained model from the web should be aware of its biases. Existing approaches for bias identification rely on datasets containing labels for the task of interest, something that a non-expert may not have access…

Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in…

Face recognition has made remarkable strides, driven by the expanding scale of datasets, advancements in various backbone and discriminative losses. However, face recognition performance is heavily affected by the label noise, especially…

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…

Deep learning with noisy labels presents significant challenges. In this work, we theoretically characterize the role of label noise from a feature learning perspective. Specifically, we consider a signal-noise data distribution, where each…

Label noise and ambiguities between similar classes are challenging problems in developing new models and annotating new data for semantic segmentation. In this paper, we propose Compensation Learning in Semantic Segmentation, a framework…

Improper or erroneous labelling can pose a hindrance to reliable generalization for supervised learning. This can have negative consequences, especially for critical fields such as healthcare. We propose an effective new approach for…

Exploration of bias has significant impact on the transparency and applicability of deep learning pipelines in medical settings, yet is so far woefully understudied. In this paper, we consider two separate groups for which training data is…

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

Predicting all applicable labels for a given image is known as multi-label classification. Compared to the standard multi-class case (where each image has only one label), it is considerably more challenging to annotate training data for…

With the proliferation of algorithmic decision-making, increased scrutiny has been placed on these systems. This paper explores the relationship between the quality of the training data and the overall fairness of the models trained with…

The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical images requires domain knowledge and can…

Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded…

Label noise in training data can significantly degrade a model's generalization performance for supervised learning tasks. Here we focus on the problem that noisy labels are primarily mislabeled samples, which tend to be concentrated near…

Despite the rapid development and great success of machine learning models, extensive studies have exposed their disadvantage of inheriting latent discrimination and societal bias from the training data. This phenomenon hinders their…

We investigate the problem of reliably assessing group fairness when labeled examples are few but unlabeled examples are plentiful. We propose a general Bayesian framework that can augment labeled data with unlabeled data to produce more…

Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight…