Search Results for author:
Found 5 papers, 0 papers with code
A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
Recent advancements in Vision-Language Models (VLMs) have enabled complex multimodal tasks by processing text and image data simultaneously, significantly enhancing the field of artificial intelligence.
FADES: Fair Disentanglement with Sensitive Relevance
Learning fair representation in deep learning is essential to mitigate discriminatory outcomes and enhance trustworthiness.
Difficulty-Based Sampling for Debiased Contrastive Representation Learning
We theoretically show that the triplet loss amplifies the bias in self-supervised representation learning.
Group-Aware Threshold Adaptation for Fair Classification
As we only need an estimated probability distribution of model output instead of the classification model structure, our post-processing model can be applied to a wide range of classification models and improve fairness in a model-agnostic manner and ensure privacy.
Adversarial Fairness Network
To achieve this goal, we reformulate the data input by eliminating the sensitive information and strengthen model fairness by minimizing the marginal contribution of the sensitive feature.
