2 papers
cs.CL2024
Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Models
Heerin Yang, Sseung-won Hwang, Jungmin So
Although pre-trained language models show good performance on various natural language processing tasks, they often rely on non-causal features and patterns to determine the outcom…
cs.CV2024
SMCL: Saliency Masked Contrastive Learning for Long-tailed Recognition
Sanglee Park, Seung-won Hwang, Jungmin So
Real-world data often follow a long-tailed distribution with a high imbalance in the number of samples between classes. The problem with training from imbalanced data is that some…