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.
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.
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.
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.
arXiv:2607. 06982v1 Announce Type: cross Abstract: Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks.
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.
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.
arXiv:2607. 22583v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities.
The paper introduces RAMP, a method for robust adaptive mixed‑precision quantization of vision models on edge CPUs. It evaluates 13 sensitivity metrics across four neural networks, finding that Jensen‑Shannon Divergence consistently identifies layers that can be safely quantized. Using K‑Means clustering on these metrics, RAMP achieves near‑lossless accuracy with an average 1.81× speed‑up, while cautioning against excluding low‑speed‑up layers that can fragment the computational graph.
Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inference latency while preserving accuracy. Howeve...
arXiv:2606. 13740v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) accelerate generation by denoising multiple tokens in parallel, making them attractive for latency-sensitive mobile inference.
The paper presents a novel multi‑exit computational scheme for TinyML on an ultra‑low‑power GAP9 SoC, adding confidence‑based gating points to a MobileNetV2 CNN for ImageNet‑100. By allowing inference to stop early, the approach cuts average MAC operations by 41 % (from 313 MMAC to 185 MMAC), reduces inference time by 29 % (49 ms to 35 ms), and saves 24 % in energy (2.1 mJ to 1.6 mJ per frame) with only a ~1 % drop in accuracy. Compared to a state‑of‑the‑art adaptive CNN on the same hardware, the method more than doubles computational efficiency, raising MAC/cycle from 8.1 to 17.2.
GaLe is a memory‑efficient technique that allows pretrained neural networks to run on resource‑constrained devices without retraining. It splits feature maps into a local exact component that keeps fine details and a global approximate component that preserves long‑range dependencies, enabling global operations and attention mechanisms typical of hybrid CNN‑transformer models. On ImageNet, GaLe matches exact‑inference accuracy while delivering up to 65% speedup and 90% RAM reduction on a Cortex‑M33, and it works across classification, detection, and generation tasks.