相关论文: Multi Attribute Bias Mitigation via Representation…

Modern machine learning datasets can have biases for certain representations that are leveraged by algorithms to achieve high performance without learning to solve the underlying task. This problem is referred to as "representation bias".…

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…

Research on Large Language Models (LLMs) has often neglected subtle biases that, although less apparent, can significantly influence the models' outputs toward particular social narratives. This study addresses two such biases within LLMs:…

Addressing bias in the trained machine learning system often requires access to sensitive attributes. In practice, these attributes are not available either due to legal and policy regulations or data unavailability for a given demographic.…

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

Facial analysis models are increasingly applied in real-world applications that have significant impact on peoples' lives. However, as literature has shown, models that automatically classify facial attributes might exhibit algorithmic…

Representation learning approaches typically rely on images of objects captured from a single perspective that are transformed using affine transformations. Additionally, self-supervised learning, a successful paradigm of representation…

Multi-label Recognition (MLR) involves assigning multiple labels to each data instance in an image, offering advantages over single-label classification in complex scenarios. However, it faces the challenge of annotating all relevant…

Continual learning of vision-language models (VLMs) focuses on leveraging cross-modal pretrained knowledge to incrementally adapt to expanding downstream tasks and datasets, while tackling the challenge of knowledge forgetting. Existing…

Measuring biases of vision systems with respect to protected attributes like gender and age is critical as these systems gain widespread use in society. However, significant correlations between attributes in benchmark datasets make it…

The widespread adoption of generative AI models has raised growing concerns about representational harm and potential discriminatory outcomes. Yet, despite growing literature on this topic, the mechanisms by which bias emerges - especially…

Scene Graph Generation (SGG) provides basic language representation of visual scenes, requiring models to grasp complex and diverse semantics between objects. This complexity and diversity in SGG leads to underrepresentation, where parts of…

Multi-instance learning (MIL) deals with tasks where data is represented by a set of bags and each bag is described by a set of instances. Unlike standard supervised learning, only the bag labels are observed whereas the label for each…

The field of self-supervised 3D representation learning has emerged as a promising solution to alleviate the challenge presented by the scarcity of extensive, well-annotated datasets. However, it continues to be hindered by the lack of…

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…

Self-supervised learning (SSL) has demonstrated its effectiveness in learning representations through comparison methods that align with human intuition. However, mainstream SSL methods heavily rely on high body datasets with single label,…

Bias mitigation in machine learning models is imperative, yet challenging. While several approaches have been proposed, one view towards mitigating bias is through adversarial learning. A discriminator is used to identify the bias…

Gender bias in vision-language models (VLMs) can reinforce harmful stereotypes and discrimination. In this paper, we focus on mitigating gender bias towards vision-language tasks. We identify object hallucination as the essence of gender…

Multi-view (or -modality) representation learning aims to understand the relationships between different view representations. Existing methods disentangle multi-view representations into consistent and view-specific representations by…

Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations. Although existing works often handle this issue based on…