- TL;DR: We propose a model for few-shot classification that incorporates explicit prior which construct class representatives that are orthogonal to the local average of closely related class representatives.
- Abstract: Few-shot classification may involve differentiating data that belongs to a different level of labels granularity. Compounded by the fact that the number of available labeled examples are scarce in the novel classification set, relying solely on the loss function to implicitly guide the classifier to separate data based on its label might not be enough; few-shot classifier needs to be very biased to perform well. In this paper, we propose a model that incorporates a simple prior: focusing on differences by building a dissimilar set of class representations. The model treats a class representation as a vector and removes its component that is shared among closely related class representatives. It does so through the combination of learned attention and vector orthogonalization. Our model works well on our newly introduced dataset, Hierarchical-CIFAR, that contains different level of labels granularity. It also substantially improved the performance on fine-grained classification dataset, CUB; whereas staying competitive on standard benchmarks such as mini-Imagenet, Omniglot, and few-shot dataset derived from CIFAR.
- Keywords: Deep learning, few-shot learning