Tensor feature hallucination for few-shot learning. (arXiv:2106.05321v2 [cs.CV] UPDATED)

Few-shot learning addresses the challenge of learning how to address novel
tasks given not just limited supervision but limited data as well. An
attractive solution is synthetic data generation. However, most such methods
are overly sophisticated, focusing on high-quality, realistic data in the input
space. It is unclear whether adapting them to the few-shot regime and using
them for the downstream task of classification is the right approach. Previous
works on synthetic data generation for few-shot classification focus on
exploiting …

arxiv cv few-shot learning learning