Related papers: Feature and Label Embedding Spaces Matter in Addre…

Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. In this paper, we propose a novel approach to address bias by leveraging pixel image attributions to identify and regularize regions of…

In this paper, we present an empirical study on image recognition fairness, i.e., extreme class accuracy disparity on balanced data like ImageNet. We experimentally demonstrate that classes are not equal and the fairness issue is prevalent…

Segmentation uncertainty models predict a distribution over plausible segmentations for a given input, which they learn from the annotator variation in the training set. However, in practice these annotations can differ systematically in…

Label noise poses an important challenge in machine learning, especially in deep learning, in which large models with high expressive power dominate the field. Models of that kind are prone to memorizing incorrect labels, thereby harming…

Recent advancements in GANs and diffusion models have enabled the creation of high-resolution, hyper-realistic images. However, these models may misrepresent certain social groups and present bias. Understanding bias in these models remains…

Past research has demonstrated that the explicit use of protected attributes in machine learning can improve both performance and fairness. Many machine learning algorithms, however, cannot directly process categorical attributes, such as…

Ensuring fairness in image classification prevents models from perpetuating and amplifying bias. Concept bottleneck models (CBMs) map images to high-level, human-interpretable concepts before making predictions via a sparse, one-layer…

How discriminative position information is for image classification depends on the data. On the one hand, the camera position is arbitrary and objects can appear anywhere in the image, arguing for translation invariance. At the same time,…

Multi-label classification has received considerable interest in recent years. Multi-label classifiers have to address many problems including: handling large-scale datasets with many instances and a large set of labels, compensating…

Bias has been a constant in face recognition models. Over the years, researchers have looked at it from both the model and the data point of view. However, their approach to mitigation of data bias was limited and lacked insight on the real…

We find that the way we choose to represent data labels can have a profound effect on the quality of trained models. For example, training an image classifier to regress audio labels rather than traditional categorical probabilities…

In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem. In order to better learn the correlations among images features, as well as labels, we attempt to explore a latent space,…

Deep neural networks usually benefit from unsupervised pre-training, e.g. auto-encoders. However, the classifier further needs supervised fine-tuning methods for good discrimination. Besides, due to the limits of full-connection, the…

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

The amount of information in the form of features and variables avail- able to machine learning algorithms is ever increasing. This can lead to classifiers that are prone to overfitting in high dimensions, high di- mensional models do not…

Medical diagnosis might fail due to bias. In this work, we identified class-feature bias, which refers to models' potential reliance on features that are strongly correlated with only a subset of classes, leading to biased performance and…

Classifier chains have recently been proposed as an appealing method for tackling the multi-label classification task. In addition to several empirical studies showing its state-of-the-art performance, especially when being used in its…

Disaggregated performance metrics across demographic groups are a hallmark of fairness assessments in computer vision. These metrics successfully incentivized performance improvements on person-centric tasks such as face analysis and are…

Learning a classifier from ambiguously labeled face images is challenging since training images are not always explicitly-labeled. For instance, face images of two persons in a news photo are not explicitly labeled by their names in the…

The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. \emph{Bias} in the data can adversely affect this decision-making. We present a new mitigation strategy to…