提出ARC架构，让隐式神经表示更懂局部特征，提升高分辨率图像分类表现。
ARC: Anchored Representation Clouds for High-Resolution INR Classification
- 用空间锚点显式建模图像局部特征，替代传统全连接结构
- 在低/高分辨率图像上均达当前最优分类性能
- 对图像平移变换更鲁棒，适合高精度视觉任务
隐式神经表示（INRs）以神经网络权重编码信号，实现内存高效且采样分辨率与资源成本解耦。现有INR图像分类方法仅在低分辨率数据上验证，且对图像空间变换敏感。我们归因于当前INRs采用全局全连接MLP架构，缺乏局部表征机制：MLPs对绝对位置敏感，难以捕捉高频细节。本文提出ARC：锚定表示云，通过在图像空间显式锚定潜在向量，引入空间结构，使模型能有效捕获局部图像信息。实验表明，该方法在低、高分辨率图像分类上均达到当前最优性能，并显著提升对图像空间平移的鲁棒性。代码已开源：https://github.com/JLuij/anchored_representation_clouds。
原文摘要 · Abstract (English)
Implicit neural representations (INRs) encode signals in neural network weights as a memory-efficient representation, decoupling sampling resolution from the associated resource costs. Current INR image classification methods are demonstrated on low-resolution data and are sensitive to image-space transformations. We attribute these issues to the global, fully-connected MLP neural network architecture encoding of current INRs, which lack mechanisms for local representation: MLPs are sensitive to absolute image location and struggle with high-frequency details. We propose ARC: Anchored Representation Clouds, a novel INR architecture that explicitly anchors latent vectors locally in image-space. By introducing spatial structure to the latent vectors, ARC captures local image data which in our testing leads to state-of-the-art implicit image classification of both low- and high-resolution images and increased robustness against image-space translation. Code can be found at https://github.com/JLuij/anchored_representation_clouds.
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。