MetaLab: Few-Shot Game Changer for Image Recognition

TL;DR

MetaLab introduces a novel few-shot image recognition method using dual neural networks for domain transformation and mutual learning, achieving near-human accuracy with minimal samples.

Contribution

The paper presents CIELab-Guided Coherent Meta-Learning, a new approach combining LabNet and LabGNN for improved few-shot image recognition performance.

Findings

Achieves up to 99% accuracy on benchmarks

Demonstrates robust performance with one-shot samples

Approaches human recognition ceiling

Abstract

Difficult few-shot image recognition has significant application prospects, yet remaining the substantial technical gaps with the conventional large-scale image recognition. In this paper, we have proposed an efficient original method for few-shot image recognition, called CIELab-Guided Coherent Meta-Learning (MetaLab). Structurally, our MetaLab comprises two collaborative neural networks: LabNet, which can perform domain transformation for the CIELab color space and extract rich grouped features, and coherent LabGNN, which can facilitate mutual learning between lightness graph and color graph. For sufficient certification, we have implemented extensive comparative studies on four coarse-grained benchmarks, four fine-grained benchmarks, and four cross-domain few-shot benchmarks. Specifically, our method can achieve high accuracy, robust performance, and effective generalization capability with one-shot sample per class. Overall, all experiments have demonstrated that our MetaLab can approach 99\% $\uparrow\downarrow$ accuracy, reaching the human recognition ceiling with little visual deviation.