Related papers: Assessing Dataset Bias in Computer Vision

Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…

Recent research suggests that predictions made by machine-learning models can amplify biases present in the training data. When a model amplifies bias, it makes certain predictions at a higher rate for some groups than expected based on…

It is well known that deep learning approaches to face recognition and facial landmark detection suffer from biases in modern training datasets. In this work, we propose to use synthetic face images to reduce the negative effects of dataset…

The availability of training data is one of the main limitations in deep learning applications for medical imaging. Data augmentation is a popular approach to overcome this problem. A new approach is a Machine Learning based augmentation,…

Despite the large volume of face recognition datasets, there is a significant portion of subjects, of which the samples are insufficient and thus under-represented. Ignoring such significant portion results in insufficient training data.…

NLP models often rely on superficial cues known as dataset biases to achieve impressive performance, and can fail on examples where these biases do not hold. Recent work sought to develop robust, unbiased models by filtering biased examples…

Face recognition (FR) systems have a growing effect on critical decision-making processes. Recent works have shown that FR solutions show strong performance differences based on the user's demographics. However, to enable a trustworthy FR…

Interdisciplinary research is often at the core of scientific progress. This dissertation explores some advantageous synergies between machine learning, cognitive science and neuroscience. In particular, this thesis focuses on vision and…

CNNs have become one of the most commonly used computational tool in the past two decades. One of the primary downsides of CNNs is that they work as a ``black box", where the user cannot necessarily know how the image data are analyzed, and…

Diffusion Models (DMs) have emerged as powerful generative models with unprecedented image generation capability. These models are widely used for data augmentation and creative applications. However, DMs reflect the biases present in the…

Face quality assessment aims at estimating the utility of a face image for the purpose of recognition. It is a key factor to achieve high face recognition performances. Currently, the high performance of these face recognition systems come…

Group imbalance, resulting from inadequate or unrepresentative data collection methods, is a primary cause of representation bias in datasets. Representation bias can exist with respect to different groups of one or more protected…

Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardware. State-of-the-art methods for most vision tasks for…

Dataset replication is a useful tool for assessing whether improvements in test accuracy on a specific benchmark correspond to improvements in models' ability to generalize reliably. In this work, we present unintuitive yet significant ways…

Our society collects data on people for a wide range of applications, from building a census for policy evaluation to running meaningful clinical trials. To collect data, we typically sample individuals with the goal of accurately…

Predictive models often reinforce biases which were originally embedded in their training data, through skewed decisions. In such cases, mitigation methods are critical to ensure that, regardless of the prevailing disparities, model…

This article investigates the critical issue of dataset bias in medical imaging, with a particular emphasis on racial disparities caused by uneven population distribution in dataset collection. Our analysis reveals that medical segmentation…

Computer vision models learn to perform a task by capturing relevant statistics from training data. It has been shown that models learn spurious age, gender, and race correlations when trained for seemingly unrelated tasks like activity…

Denoising diffusion models have emerged as a dominant approach for image generation, however they still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be…

We consider the problem of learning from data corrupted by underrepresentation bias, where positive examples are filtered from the data at different, unknown rates for a fixed number of sensitive groups. We show that with a small amount of…