用机器学习预测SIREN编码误差，提速百倍
Predicting the Encoding Error of SIRENs
- 构建30万条数据的SIREN编码误差预测模型
- 毫秒级预估误差，比训练快100倍以上
- 揭示网络宽度与误差波动的关系，适合压缩研究者
隐式神经表示（INRs）将图像、视频和3D形状等信号编码为神经网络权重，广泛应用于信号压缩。在保持高保真度的同时，需权衡网络规模、训练与推理时间。但训练INRs计算成本高，难以快速找到最优折衷方案。本文提出一种方法，可基于网络超参数和待编码信号，预测典型INR模型SIREN的编码误差。该方法在包含30万条SIREN的唯一数据集上训练完成（数据集见：https://huggingface.co/datasets/predict-SIREN-PSNR/COIN-collection）。预测模型验证了该回归问题的可行性，使用户可在毫秒内预估编码误差，远快于实际训练所需分钟级时间。同时揭示了窄SIREN存在极高随机误差波动的原因，并发现其性能与JPEG压缩有相似规律。
原文摘要 · Abstract (English)
Implicit Neural Representations (INRs), which encode signals such as images, videos, and 3D shapes in the weights of neural networks, are becoming increasingly popular. Among their many applications is signal compression, for which there is great interest in achieving the highest possible fidelity to the original signal subject to constraints such as neural network size, training (encoding) and inference (decoding) time. But training INRs can be a computationally expensive process, making it challenging to determine the best possible tradeoff under such constraints. Towards this goal, we present a method which predicts the encoding error that a popular INR network (SIREN) will reach, given its network hyperparameters and the signal to encode. This method is trained on a unique dataset of 300,000 SIRENs, trained across a variety of images and hyperparameters. (Dataset available here: https://huggingface.co/datasets/predict-SIREN-PSNR/COIN-collection.) Our predictive method demonstrates the feasibility of this regression problem, and allows users to anticipate the encoding error that a SIREN network will reach in milliseconds instead of minutes or longer. We also provide insights into the behavior of SIREN networks, such as why narrow SIRENs can have very high random variation in encoding error, and how the performance of SIRENs relates to JPEG compression.
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。