AI RESEARCH
Tensor-Augmented Convolutional Neural Networks: Enhancing Expressivity with Generic Tensor Kernels
arXiv CS.CV
•
ArXi:2604.08072v1 Announce Type: new Convolutional Neural Networks (CNNs) excel at extracting local features hierarchically, but their performance in capturing complex correlations hinges heavily on deep architectures, which are usually computationally demanding and difficult to interpret. To address these issues, we propose a physically-guided shallow model: tensor-augmented CNN (TACNN), which replaces conventional convolution kernels with generic tensors to enhance representational capacity.