
Flatness-seeking training objectives, such as sharpness-aware minimization (SAM), can improve the generalization of backbones in few-shot classification tasks, outperforming state-of-the-art methods.


coremsg

flatness-aware-backbone-training-improves-generalization-in-few-shot-classification


Flatness-Aware Backbone Training Improves Generalization in Few-Shot Classification


title_rewrite


FusionShot, a focal diversity optimized few-shot ensemble learning approach, can boost the robustness and generalization performance of pre-trained few-shot models by intelligently integrating the complementary wisdom of multiple independently trained few-shot models.


robust-few-shot-ensemble-learning-with-focal-diversity-based-pruning


Robust Few-Shot Ensemble Learning with Focal Diversity-Based Pruning
