Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
arXiv:2003.09338
Abstract
Popular approaches for few-shot classification consist of first learning a generic data representation based on a large annotated dataset, before adapting the representation to new classes given only a few labeled samples. In this work, we propose a new strategy based on feature selection, which is both simpler and more effective than previous feature adaptation approaches. First, we obtain a multi-domain representation by training a set of semantically different feature extractors. Then, given a few-shot learning task, we use our multi-domain feature bank to automatically select the most relevant representations. We show that a simple non-parametric classifier built on top of such features produces high accuracy and generalizes to domains never seen during training, which leads to state-of-the-art results on MetaDataset and improved accuracy on mini-ImageNet.
arXiv commentECCV'20
References in corpus (15)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- ADADELTA: An Adaptive Learning Rate Method
- Prototypical Networks for Few-shot Learning
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Unsupervised Representation Learning by Predicting Image Rotations
- Fine-Grained Visual Classification of Aircraft
- Meta-Learning for Semi-Supervised Few-Shot Classification
- Spectral Norm Regularization for Improving the Generalizability of Deep Learning
- Meta-Learning with Latent Embedding Optimization
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
- Universal representations:The missing link between faces, text, planktons, and cat breeds
- Conditional Neural Processes
- A Kernel Perspective for Regularizing Deep Neural Networks
- Optimized Generic Feature Learning for Few-shot Classification across Domains