新方法通过自适应频谱门控增强隐式神经表示

报道来源 [4]

1. arXiv cs.LG TIER_1 English(EN) · Preston Pitzer, Anish Pradhan, Harpreet S. Dhillon · 2026-07-03 04:00

   神经特征学习的傅里叶预处理

   arXiv:2607.02199v1 Announce Type: cross Abstract: Mutual information (MI)-inspired feature learning techniques are capable of generating low-dimensional embeddings that retain nonlinear dependence structures, but direct estimations of MI suffer from noisy probability distribution…

2. arXiv cs.LG TIER_1 English(EN) · Harpreet S. Dhillon · 2026-07-02 14:07

   神经特征学习的傅里叶预处理

   Mutual information (MI)-inspired feature learning techniques are capable of generating low-dimensional embeddings that retain nonlinear dependence structures, but direct estimations of MI suffer from noisy probability distribution estimates in the low-data regime. The H-Score obj…

3. arXiv cs.LG TIER_1 English(EN) · Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti, Luigi Di Stefano · 2026-06-30 04:00

   基于阻尼振荡的谱门控用于自适应隐式神经表示

   arXiv:2606.23129v2 Announce Type: replace-cross Abstract: Implicit Neural Representations (INRs) have been proven successful in encoding continuous signals through coordinate-based networks, yet facing a spectral dilemma: periodic activations capture fine details but act as all-p…

4. arXiv cs.CV TIER_1 English(EN) · Harinandan Shukla, Rajarshi Verma, Jitin Singla · 2026-06-30 04:00

   FiRe: 频率重参数化作为周期性隐式神经表示的预条件器

   arXiv:2606.29414v1 Announce Type: new Abstract: Periodic Implicit Neural Representations (INRs) such as SIREN and FINER assign every neuron, the same global frequency, spending the representational budget inefficiently when local signal content varies. We introduce FiRe (Frequenc…