A Unifying Tensor View for Lightweight CNNs
Not on the map. Why?
Abstract (arXiv)
Despite the decomposition of convolutional kernels for lightweight CNNs being well studied, existing works that rely on tensor network diagrams or hyperdimensional abstraction lack geometry intuition. This work devises a new perspective by linking a 3D-reshaped kernel tensor to its various slice-wise and rank-1 decompositions, permitting a straightforward connection between various tensor approximations and efficient CNN modules. Specifically, it is discovered that a pointwise-depthwise-pointwise (PDP) configuration constitutes a viable construct for lightweight CNNs. Moreover, a novel link to the latest ShiftNet is established, inspiring a first-ever shift layer pruning that achieves nearly 50% compression with < 1% drop in accuracy for ShiftResNet.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 7 of its 7 references that are in the map. First posted on arXiv 15 Dec 2023.
Builds on
7 of 7 references.
References · 7
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
- 2014Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decompositioncited by 199
- 2015Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applicationscited by 161
- 2019All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classificationcited by 38
- 2018Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compressioncited by 9
- 2018Rank Selection of CP-decomposed Convolutional Layers with Variational Bayesian Matrix Factorizationcited by 5
Built on by
Not cited yet.