Low-shot Visual Recognition by Shrinking and Hallucinating Features

3个组成

It employs a learner, two training phases, and one testing phase.

1. learner

The learner is assumed to be composed of a feature extractor and a multi-class classifier.

2. traing phased one （representation learning）

During representation learning (training phase one), the
learner receives a fixed set of base categories $C_{base}$, and a dataset D containing a large number of examples for each category in Cbase. The learner uses D to set the parameters of its feature extractor.

产生新的类别

Any two examples z1 and z2 belonging to the same category represent a plausible transformation. Then, given a novel category example x, we want to apply to x the transformation that sent z1 to z2. That is, we want to complete the transformation “analogy” z1 : z2 :: x : ?.

We do this by training a function G that takes as input the concatenated feature vectors of the three examples [φ(x), φ(z1), φ(z2)].G是MLP

3. second phase （low-shot learning）

the learner is given a set of categories $C_l$ that it must learn to distinguish. $C_l$ = $C_{base}$ $\cup$ $C_{novel}$ is a mix of base categories Cbase, and unseen novel categories Cnovel.
对于$C_{novel}$，仅仅有k-shot

4.testing phase

the learnt model predicts labels from the combined label space $C_l$ = $C_{base}$ $\cup$ $C_{novel}$ on a set of previously unseen test images.

模型（Learning to generate new examples）

核心：，通过z1:z2,类比x:?.

利用D训练G， 为用于类比的2组双胞胎。预测结果为：。损失函数。与上文中的特征表达误差与分类误差对应。