68 citations · 75 across the 11 of their papers we have counts for
4 papers · 1 filter
BendVLM: Test-Time Debiasing of Vision-Language Embeddings
Walter Gerych, Haoran Zhang, Kimia Hamidieh +4
Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members o…
Identifying Implicit Social Biases in Vision-Language Models
Kimia Hamidieh, Haoran Zhang, Walter Gerych +2
Vision-language models, like CLIP (Contrastive Language Image Pretraining), are becoming increasingly popular for a wide range of multimodal retrieval tasks. However, prior work ha…
Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection
Saachi Jain, Kimia Hamidieh, Kristian Georgiev +3
Machine learning models can fail on subgroups that are underrepresented during training. While techniques such as dataset balancing can improve performance on underperforming group…
Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation
Kimia Hamidieh, Haoran Zhang, Swami Sankaranarayanan +1
Supervised learning methods have been found to exhibit inductive biases favoring simpler features. When such features are spuriously correlated with the label, this can result in s…