Shih‐Fu Chang

Uncertainty-Aware Few-Shot Image Classification

2020 · arXiv (Cornell University)

Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the support set …

DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection

2023 · arXiv (Cornell University)

Generalized few-shot object detection aims to achieve precise detection on both base classes with abundant annotations and novel classes with limited training data. Existing approaches enhance few-shot generalization with the sacrifice of base-class performance, or …