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

arXiv: https://arxiv.org/abs/2007.08461 · HTML: https://mlsanity.com/paper/2007.08461/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 16 of 16)

- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning](https://mlsanity.com/paper/2109.05749/) (2021)
- [Reliable Few-shot Learning under Dual Noises](https://mlsanity.com/paper/2506.16330/) (2025)
- [Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels](https://mlsanity.com/paper/2203.07788/) (2022)
- [Towards Global Optimal Visual In-Context Learning Prompt Selection](https://mlsanity.com/paper/2405.15279/) (2024)
- [Learnable Distribution Calibration for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2210.00232/) (2022)
- [An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2209.13777/) (2022)
- [Prototype Completion for Few-Shot Learning](https://mlsanity.com/paper/2108.05010/) (2021)
- [Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning](https://mlsanity.com/paper/2109.01295/) (2021)
- [A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning](https://mlsanity.com/paper/2110.11128/) (2021)
- [Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels](https://mlsanity.com/paper/2301.00545/) (2023)
- [Task Adaptive Feature Transformation for One-Shot Learning](https://mlsanity.com/paper/2304.06832/) (2023)
- [Rapid COVID-19 Risk Screening by Eye-region Manifestations](https://mlsanity.com/paper/2106.06664/) (2021)
- [Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition](https://mlsanity.com/paper/2209.03034/) (2022)
- [Color as the Impetus: Transforming Few-Shot Learner](https://mlsanity.com/paper/2507.22136/) (2025)
- [PathCo-LatticE: Pathology-Constrained Lattice-Of Experts Framework for Fully-supervised Few-Shot Cardiac MRI Segmentation](https://mlsanity.com/paper/2512.09779/) (2025)

## Abstract (arXiv)

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.