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

07/15/2020
by   Yikai Wang, et al.
14

Deep learning based models have excelled in many computer vision task 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. Learning from such extremely limited labeled examples is known as Few-shot learning. 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 to exploit the support of unlabeled instances for few-shot visual recognition. Typically, we repurpose the self-taught learning paradigm. To do so, we construct 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 corresponding pseudo-labeled instance. We rank the credibility of pseudo-labels of unlabeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances.This process is repeated until all the unlabeled samples are iteratively included in the expanded training set. Theoretically, under mild conditions of restricted eigenvalue, irrepresentability, and large error, our approach is guaranteed to collect all the correctly-predicted pseudo-labeled instances from the noisy pseudo-labeled set. Extensive experiments under two few-shot settings show that our approach can establish new state of the art on four widely used few-shot visual recognition benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB.

READ FULL TEXT

page 3

page 4

page 5

page 7

page 8

page 9

page 11

page 12

research
03/26/2020

Instance Credibility Inference for Few-Shot Learning

Few-shot learning (FSL) aims to recognize new objects with extremely lim...
research
09/07/2021

Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis

We study the few-shot learning (FSL) problem, where a model learns to re...
research
05/18/2018

Self-Training Ensemble Networks for Zero-Shot Image Recognition

Despite the advancement of supervised image recognition algorithms, thei...
research
12/14/2020

Iterative label cleaning for transductive and semi-supervised few-shot learning

Few-shot learning amounts to learning representations and acquiring know...
research
11/29/2021

Self-Training of Halfspaces with Generalization Guarantees under Massart Mislabeling Noise Model

We investigate the generalization properties of a self-training algorith...
research
02/07/2018

VISER: Visual Self-Regularization

In this work, we propose the use of large set of unlabeled images as a s...
research
03/20/2023

A Global Model Approach to Robust Few-Shot SAR Automatic Target Recognition

In real-world scenarios, it may not always be possible to collect hundre...

Please sign up or login with your details

Forgot password? Click here to reset