Instance Credibility Inference for Few-Shot Learning
arXiv:2003.11853
Abstract
Few-shot learning (FSL) aims to recognize new objects with extremely limited training data for each category. Previous efforts are made by either leveraging meta-learning paradigm or novel principles in data augmentation to alleviate this extremely data-scarce problem. In contrast, this paper presents a simple statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the distribution support of unlabeled instances for few-shot learning. Specifically, we first train a linear classifier with the labeled few-shot examples and use it to infer the pseudo-labels for the unlabeled data. To measure the credibility of each pseudo-labeled instance, we then propose to solve another linear regression hypothesis by increasing the sparsity of the incidental parameters and rank the pseudo-labeled instances with their sparsity degree. We select the most trustworthy pseudo-labeled instances alongside the labeled examples to re-train the linear classifier. This process is iterated until all the unlabeled samples are included in the expanded training set, i.e. the pseudo-label is converged for unlabeled data pool. Extensive experiments under two few-shot settings show that our simple approach can establish new state-of-the-arts on four widely used few-shot learning benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB. Our code is available at: https://github.com/Yikai-Wang/ICI-FSL
accepted by CVPR 2020
References in corpus (18)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Prototypical Networks for Few-shot Learning
- How transferable are features in deep neural networks?
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
- Meta-Learning for Semi-Supervised Few-Shot Classification
- On First-Order Meta-Learning Algorithms
- DropBlock: A regularization method for convolutional networks
- Self-training with Noisy Student improves ImageNet classification
- Learning to Self-Train for Semi-Supervised Few-Shot Classification
- Meta-Learning with Latent Embedding Optimization
- Few-Shot Learning with Metric-Agnostic Conditional Embeddings
- Learning to Learn: Meta-Critic Networks for Sample Efficient Learning
- Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
- A Blockwise Descent Algorithm for Group-penalized Multiresponse and Multinomial Regression
- Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning
- Image Deformation Meta-Networks for One-Shot Learning
- Partial Consistency with Sparse Incidental Parameters