We introduce the Deep Edge Filter, a novel approach that applies high-pass filtering to deep neural network features to improve model generalizability. Our method is motivated by our hypothesis that neural networks encode task-relevant semantic information in high-frequency components while storing domain-specific biases in low-frequency components of deep features. By subtracting low-pass filtered outputs from original features, our approach isolates generalizable representations while preserving architectural integrity. Experimental results across diverse domains such as Vision, Text, 3D, and Audio demonstrate consistent performance improvements regardless of model architecture and data modality. Analysis reveals that our method induces feature sparsification and effectively isolates high-frequency components, providing empirical validation of our core hypothesis. The code is available at https://github.com/dongkwani/DeepEdgeFilter.

翻译：我们提出了深度边缘滤波器，这是一种新颖的方法，通过对深度神经网络特征应用高通滤波来提高模型的泛化能力。我们的方法基于以下假设：神经网络在深层特征的高频分量中编码任务相关的语义信息，而在低频分量中存储领域特定的偏差。通过从原始特征中减去低通滤波后的输出，我们的方法能够分离出可泛化的表示，同时保持架构的完整性。在视觉、文本、3D和音频等多个领域的实验结果表明，无论模型架构和数据模态如何，该方法都能带来一致的性能提升。分析表明，我们的方法能诱导特征稀疏化并有效分离高频分量，为核心假设提供了实证验证。代码可在 https://github.com/dongkwani/DeepEdgeFilter 获取。