Skip to yearly menu bar Skip to main content

Workshop: Workshop on robustness of zero/few-shot learning in foundation models (R0-FoMo)

Divide and Conquer: Two-Level Problem Remodeling for Large-Scale Few-Shot Learning

Mohamadreza Fereydooni · Hosein Hasani · Ali Razghandi · Mahdieh Soleymani


Few-shot learning methods have achieved notable performance in recent years. However, few-shot learning in large-scale settings with hundreds of classes is still challenging.In this paper, we tackle the problems of large-scale few-shot learning by taking advantage of pre-trained foundation models. We recast the original problem in two levels with different granularity. At the coarse-grained level, we introduce a novel object recognition approach with robustness to sub-population shifts. At the fine-grained level, generative experts are designed for few-shot learning, specialized for different superclasses.A Bayesian schema is considered to combine coarse-grained information with fine-grained predictions in a winner-takes-all fashion.Extensive experiments on large-scale datasets and different architectures show that the proposed method is both effective and efficient besides its simplicity and natural problem remodeling. The code is publicly available at

Chat is not available.