将不固定特征输入转为图像，让任意视觉模型都能处理。
Haphazard Inputs as Images in Online Learning
- 动态输入转为固定尺寸图像表示，无需修改模型
- 在4个数据集上验证有效，适配ResNet与ViT等模型
- 适合想用现成视觉模型处理异构数据的研究者
在线学习中特征空间不固定的问题（即随机输入）近年来备受关注，因其在多个领域具有广泛应用前景。然而现有方法依赖特定模型，难以利用现有先进深度学习技术，而这些技术通常要求输入为固定维度。为此，我们提出一种即时将在线学习中的可变特征空间转换为固定维度图像表示的新方法。该方法简单且通用，不依赖具体模型，使任何基于视觉的模型均可直接应用于随机输入，实验中已成功应用于ResNet和ViT。图像表示无缝处理不一致输入，具备良好的可扩展性与鲁棒性。我们在四个公开数据集上验证了方法的有效性。代码已开源：https://github.com/Rohit102497/HaphazardInputsAsImages。
原文摘要 · Abstract (English)
The field of varying feature space in online learning settings, also known as haphazard inputs, is very prominent nowadays due to its applicability in various fields. However, the current solutions to haphazard inputs are model-dependent and cannot benefit from the existing advanced deep-learning methods, which necessitate inputs of fixed dimensions. Therefore, we propose to transform the varying feature space in an online learning setting to a fixed-dimension image representation on the fly. This simple yet novel approach is model-agnostic, allowing any vision-based models to be applicable for haphazard inputs, as demonstrated using ResNet and ViT. The image representation handles the inconsistent input data seamlessly, making our proposed approach scalable and robust. We show the efficacy of our method on four publicly available datasets. The code is available at https://github.com/Rohit102497/HaphazardInputsAsImages.
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。