改进SIREN的初始化，提升信号拟合精度与效率
Improving Accuracy and Efficiency of Implicit Neural Representations: Making SIREN a WINNER
- 用高斯噪声扰动SIREN权重，噪声大小由目标信号频谱中心自适应确定
- 在音频、图像和3D形状拟合上均超越基础SIREN，显著提升精度
- 无需额外可训练参数，适合对信号频谱敏感的神经表示任务
我们识别并解决了正弦表示网络（SIREN）的一个根本性局限：当未正确初始化时，SIREN难以拟合其频率支持范围之外的信号。极端情况下，若网络频率支持与目标频谱错位，会出现‘频谱瓶颈’现象，模型输出趋近零，即使对自身能力范围内的频率也无法恢复。为此，我们提出WINNER——面向神经表示的带噪声权重初始化方法。该方法对初始均匀分布的SIREN权重添加高斯噪声，噪声尺度由目标信号的频谱中心自适应决定。类似随机傅里叶嵌入，但不引入额外可训练参数，有效缓解‘频谱偏差’。实验表明，WINNER在音频拟合上达到当前最优，同时在图像与3D形状拟合中实现显著提升。该方法还为深度神经网络的自适应、目标感知初始化提供了新思路。代码与数据见 cfdlabtechnion.github.io/siren_square/
原文摘要 · Abstract (English)
We identify and address a fundamental limitation of sinusoidal representation networks (SIRENs), a class of implicit neural representations. SIRENs Sitzmann et al. (2020), when not initialized appropriately, can struggle at fitting signals that fall outside their frequency support. In extreme cases, when the network's frequency support misaligns with the target spectrum, a 'spectral bottleneck' phenomenon is observed, where the model yields to a near-zero output and fails to recover even the frequency components that are within its representational capacity. To overcome this, we propose WINNER - Weight Initialization with Noise for Neural Representations. WINNER perturbs uniformly initialized weights of base SIREN with Gaussian noise - whose noise scales are adaptively determined by the spectral centroid of the target signal. Similar to random Fourier embeddings, this mitigates 'spectral bias' but without introducing additional trainable parameters. Our method achieves state-of-the-art audio fitting and significant gains in image and 3D shape fitting tasks over base SIREN. Beyond signal fitting, WINNER suggests new avenues in adaptive, target-aware initialization strategies for optimizing deep neural network training. For code and data visit cfdlabtechnion.github.io/siren_square/.
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。