论文标题
功能地图重建网络几乎没有射击分类
Few-Shot Classification with Feature Map Reconstruction Networks
论文作者
论文摘要
在本文中，我们将很少的分类重新制定为潜在空间中的重建问题。网络从给定类的支持功能中重建查询功能映射的能力可预测该类中查询的成员资格。我们通过直接从支持功能回归到封闭形式的查询功能，而无需引入任何新的模块或大规模可学习的参数，从而引入了一种新的机制来进行几次射击分类。与以前的方法相比，所得的特征图重建网络既具有性能和计算效率。我们在四个具有不同神经体系结构的细粒基准上表现出一致而实质性的准确性提高。我们的模型还具有竞争性的，具有最小的铃铛和哨子的非精密迷你象征和分层象征基准。
In this paper we reformulate few-shot classification as a reconstruction problem in latent space. The ability of the network to reconstruct a query feature map from support features of a given class predicts membership of the query in that class. We introduce a novel mechanism for few-shot classification by regressing directly from support features to query features in closed form, without introducing any new modules or large-scale learnable parameters. The resulting Feature Map Reconstruction Networks are both more performant and computationally efficient than previous approaches. We demonstrate consistent and substantial accuracy gains on four fine-grained benchmarks with varying neural architectures. Our model is also competitive on the non-fine-grained mini-ImageNet and tiered-ImageNet benchmarks with minimal bells and whistles.
