How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning

Abstract

Deep learning based models have excelled in many computer vision tasks and appear to surpass humans' performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large number of parameters. This severely limits their scalability to the real-world long-tail distributed categories, some of which are with a large number of instances, but with only a few manually annotated. Learning from such extremely limited labeled examples is known as Few-shot learning (FSL). Different to prior arts that leverage meta-learning or data augmentation strategies to alleviate this extremely data-scarce problem, this paper presents a statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the support of unlabeled instances for few-shot visual recognition. Typically, we repurpose the self-taught learning paradigm to predict pseudo-labels of unlabeled instances with an initial classifier trained from the few shot and then select the most confident ones to augment the training set to re-train the classifier. This is achieved by constructing a (Generalized) Linear Model (LM/GLM) with incidental parameters to model the mapping from (un-)labeled features to their (pseudo-)labels, in which the sparsity of the incidental parameters indicates the credibility of the corresponding pseudo-labeled instance. We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances. Theoretically, under mild conditions of restricted eigenvalue, irrepresentability, and large error, our approach is guaranteed to collect all the correctly-predicted instances from the noisy pseudo-labeled set.

Journal extension of arXiv:2003.11853 that appears in CVPR 2020 Code and models are released at https://github.com/Yikai-Wang/ICI-FSL

References in corpus (8)

• How transferable are features in deep neural networks?
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Unsupervised Label Noise Modeling and Loss Correction
• Cross Attention Network for Few-shot Classification
• Learning to Learn: Meta-Critic Networks for Sample Efficient Learning
• TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
• Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning
• Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

Cited by in corpus (2)

• A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
• Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition