Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs
cs.LG
Submitted: 2026-08-26
Updated: 2026-08-27
Comments: 17 pages, 10 figures, accepted by MobiCom2026
Code: https://github.com/LforikCyzzz/CGS_code
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MMDetection: Open MMLab Detection Toolbox and Benchmark
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Rethinking Machine Learning Development and Deployment for Edge Devices
- Parameter Efficient Multimodal Transformers for Video Representation Learning
- More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
- Decoupled Weight Decay Regularization
- Convolutional neural networks with low-rank regularization
- Multi-Scale Context Aggregation by Dilated Convolutions
- mixup: Beyond Empirical Risk Minimization
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks