MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning

Documenti analoghi

• RC-Mixup: A Data Augmentation Strategy against Noisy Data for Regression Tasks
  di: Hwang, Seong-Hyeon, et al.
  Pubblicazione: (2024)
• GradMix: Gradient-based Selective Mixup for Robust Data Augmentation in Class-Incremental Learning
  di: Kim, Minsu, et al.
  Pubblicazione: (2025)
• T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning
  di: Hwang, Seong-Hyeon, et al.
  Pubblicazione: (2025)
• Fair Class-Incremental Learning using Sample Weighting
  di: Park, Jaeyoung, et al.
  Pubblicazione: (2024)
• SHAP-based Explanations are Sensitive to Feature Representation
  di: Hwang, Hyunseung, et al.
  Pubblicazione: (2025)