Showing cs.CVShow all
2 papers · 1 filter
cs.CV2024
Debiasing Classifiers by Amplifying Bias with Latent Diffusion and Large Language Models
Donggeun Ko, Dongjun Lee, Namjun Park +2
Neural networks struggle with image classification when biases are learned and misleads correlations, affecting their generalization and performance. Previous methods require attri…
cs.CV2024
DiffInject: Revisiting Debias via Synthetic Data Generation using Diffusion-based Style Injection
Donggeun Ko, Sangwoo Jo, Dongjun Lee +2
Dataset bias is a significant challenge in machine learning, where specific attributes, such as texture or color of the images are unintentionally learned resulting in detrimental…