Learn to Accumulate Evidence from All Training Samples: Theory and Practice

1 code implementation • 19 Jun 2023 • Deep Pandey, Qi Yu

To unveil the real cause of this undesired behavior, we theoretically investigate evidential models and identify a fundamental limitation that explains the inferior performance: existing evidential activation functions create zero evidence regions, which prevent the model to learn from training samples falling into such regions.

Multidimensional Belief Quantification for Label-Efficient Meta-Learning

1 code implementation • CVPR 2022 • Deep Pandey, Qi Yu

The proposed model formulates a multidimensional belief measure, which can quantify the known uncertainty and lower bound the unknown uncertainty of any given task.

Few-Shot Image Classification Few-Shot Learning