相关论文: BiaSwap: Removing dataset bias with bias-tailored …

Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the…

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…

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…

As one of the most successful generative models, diffusion models have demonstrated remarkable efficacy in synthesizing high-quality images. These models learn the underlying high-dimensional data distribution in an unsupervised manner.…

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…

Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge of the biases present in the training data in order to…

Deep learning models were frequently reported to learn from shortcuts like dataset biases. As deep learning is playing an increasingly important role in the modern healthcare system, it is of great need to combat shortcut learning in…

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Machine learning models trained on imbalanced datasets often exhibit intersectional biases-systematic errors arising from the interaction of multiple attributes such as object class and environmental conditions. This paper presents a…

State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended underlying task. Previous work has demonstrated effective methods to…

Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which…

Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval, and object detection. Data augmentations are a crucial aspect of pre-training robust…

Learning generalized models from biased data is an important undertaking toward fairness in deep learning. To address this issue, recent studies attempt to identify and leverage bias-conflicting samples free from spurious correlations…

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…

In this paper, we study the "dataset bias" problem from a statistical standpoint, and identify the main cause of the problem as the strong correlation between a class attribute u and a non-class attribute b in the input x, represented by…

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

Recent work has shown that deep vision models tend to be overly dependent on low-level or "texture" features, leading to poor generalization. Various data augmentation strategies have been proposed to overcome this so-called texture bias in…

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…

Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on the spuriously…

It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter at any stage of the development pipeline, models are…