arXiv Machine Learning August 27, 2026 By Hao Luo, Yiting Yang, Wenyi Zhao, Man Jiang, Zhijun Lin, Ghulam Mohiuddin, Ting Jiang, Kunming Luo, Zihao Zhang, Qingsen Yan, Guoqing Wang, Wei Dong, Peng Wang

Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs

Read the original on arXiv Machine Learning →

The paper introduces Channel Group-Shared (CGS) low‑rank approximation, a Singular Value Decomposition–based strategy that shares down/up‑projection matrices across channel groups while using lightweight diagonal matrices for each group. This design dramatically cuts the parameter count of pointwise convolutions, which dominate the size of large‑kernel CNNs such as RepLKNet, ConvNeXt, and SLaK. Experiments show that CGS‑enhanced models maintain competitive accuracy while substantially reducing storage, memory bandwidth, and loading latency, making them viable for deployment on edge devices.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

efficiency

arXiv AI

Jul 2

Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects

arXiv:2505. 03303v4 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.

By Tasnim Shahriar

fine-tuning benchmarks

arXiv AI

Jul 1

A Reproducible Benchmark of Lightweight CNNs: Accuracy, Efficiency, and the Impact of Pretrained Initialization

arXiv:2505. 03303v3 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.

By Tasnim Shahriar

fine-tuning benchmarks

arXiv Machine Learning

Jul 3

WBMM: Windowed Batch Matrix Multiplication for Efficient Large Receptive Field Convolution

arXiv:2607. 02097v1 Announce Type: cross Abstract: Large kernel depthwise convolutions achieve strong performance but suffer from significant degradation as kernel size grows due to irregular memory access from gather-based computation; while Large Kernel Acceleration (LKA) helps on small feature maps, it becomes counterproductive on large feature maps, even slower than non-accelerated implementations.

By Wan Song, Wei Zhou, Rui Wang, Jun Yu, Toru Kurihara, Jiajia Xu, Shu Zhan

efficiency benchmarks safety

arXiv Machine Learning

Jul 9

EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI

arXiv:2607. 06982v1 Announce Type: cross Abstract: Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks.

By Hao Kong, Di Liu, Shuo Huai, Xiangzhong Luo, Ravi Subramaniam, Christian Makaya, Qian Lin, Weichen Liu

computer-vision efficiency benchmarks

arXiv Machine Learning

Jul 3

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression

arXiv:2509. 25136v3 Announce Type: replace Abstract: Activation-aware low-rank factorization techniques yield strong compression results but are generally confined to linear layers, while existing whitening-based theory typically makes an implicit full-rank assumption on activations.

By David Gonz\'alez-Mart\'inez

llms fine-tuning efficiency

Hugging Face Trending Papers

Jul 8

EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI

Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks. However, the prohibitive computational cost of CNNs hinders the deployment of CNNs onto resource-constrained embedded devices.

computer-vision efficiency benchmarks

One email a morning, machine-written

Related stories

Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects

A Reproducible Benchmark of Lightweight CNNs: Accuracy, Efficiency, and the Impact of Pretrained Initialization

WBMM: Windowed Batch Matrix Multiplication for Efficient Large Receptive Field Convolution

EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression

EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI