Signals 4 · free daily AI digest

GaLe: memory-efficient Global Approximate and Local Exact features

Paper recorded by Signals 4 on 2026-09-02 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-02 on arXiv · recorded by Signals 4 on 2026-09-03

Category: cs.CV · 计算机视觉 · first seen 2026-09-03

Abstract

Embedded devices typically lack the resources of GPU-equipped machines, and existing inference methods suffer from either high computational overhead (patch-based) or accuracy loss (approximation-based). We propose GaLe, a memory-efficient technique that enables the deployment of pretrained networks on constrained devices without retraining. GaLe partitions feature maps into two components: a loca

Read on arXiv →

#174 most recent of 237 cs.CV papers we have recorded · ↑ newer: Generating Medical Image Counterfactuals using Causal Explanations · ↓ older: Genesis: A Generative Engine for Hierarchical Satellite Image Synthesi
Cite this page: GaLe: memory-efficient Global Approximate and Local Exact features: the #174 most recent of 237 cs.CV papers we have recorded (as of 2026-09-02). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/gale-memory-efficient-global-approximate-and-local-exact-features.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions