← Back to all news
arXiv Computer Vision By Alberto Ancilotto, Elisabetta Farella

GaLe: memory-efficient Global Approximate and Local Exact features

Read the original on arXiv Computer Vision →

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.

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 Computer Vision.

Related stories

arXiv Machine Learning
4d ago

Node-wise Feature Encoding for Neural Performance Prediction

FeatureFormer is a neural performance predictor that adds explicit node-wise encodings of FLOPs, parameter counts, and memory proxies to a gated graph attention architecture. It is designed to improve latency and energy prediction for neural networks on edge devices, addressing the limitation of existing GNN and transformer predictors that largely ignore node-level computational cost. The authors also introduce NNEQ, a large-scale energy consumption dataset, and show through extensive experiments that FeatureFormer achieves state‑of‑the‑art performance across both metrics, including challenging out‑of‑domain settings, while the encoding can broadly enhance existing predictors with negligible overhead.

By Matthew Grenier, William Hammer, Andrew Heuer, Nikhil Krishna, Yi Wang, Ramtin Zand
llmsbenchmarks
More like this →