Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
arXiv:2001.09849
Abstract
In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples. In this context, works have proposed to introduce Graph Neural Networks (GNNs) aiming at exploiting the information contained in other samples treated concurrently, what is commonly referred to as the transductive setting in the literature. These GNNs are trained all together with a backbone feature extractor. In this paper, we propose a new method that relies on graphs only to interpolate feature vectors instead, resulting in a transductive learning setting with no additional parameters to train. Our proposed method thus exploits two levels of information: a) transfer features obtained on generic datasets, b) transductive information obtained from other samples to be classified. Using standard few-shot vision classification datasets, we demonstrate its ability to bring significant gains compared to other works.
References in corpus (24)
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning
- Wide Residual Networks
- Theoretical Models of Learning to Learn
- Simplifying Graph Convolutional Networks
- Generalizing from a Few Examples: A Survey on Few-Shot Learning
- Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
- Manifold Mixup: Better Representations by Interpolating Hidden States
- Few-Shot Learning with Graph Neural Networks
- SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
- Meta-Learning with Latent Embedding Optimization
- A Closer Look at Few-shot Classification
- A Two-Stage Approach to Few-Shot Learning for Image Recognition
- Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
- Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
- Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
- Few-Shot Learning via Saliency-guided Hallucination of Samples
- Prototype Rectification for Few-Shot Learning
- Generalized Adaptation for Few-Shot Learning