MetaLab通过颜色空间与图神经网络协同，实现单样本图像识别接近人类水平。
MetaLab: Few-Shot Game Changer for Image Recognition
- 利用CIELab色彩空间和双图结构，实现特征与光照的联合建模。
- 在每类仅1个样本时达到接近99%准确率，跨域泛化能力强。
- 适合小样本场景下的高精度图像识别任务，如医疗影像分类。
少数样本图像识别具有广泛应用前景，但与传统大规模识别仍存在显著技术差距。本文提出一种高效的新方法——基于CIELab引导的连贯元学习（MetaLab）。该方法包含两个协同神经网络：LabNet可对CIELab色彩空间进行域变换并提取丰富分组特征；连贯LabGNN则促进明度图与色度图间的相互学习。为充分验证，我们在四个粗粒度、四个细粒度及四个跨域少样本基准上进行了广泛对比实验。结果表明，该方法在每类仅一个样本时即可实现高精度、强鲁棒性与有效泛化能力，整体性能接近99%的准确率，达到人类识别极限，视觉偏差极小。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。