AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

ELSE: Efficient Deep Neural Network Inference through Line-based Sparsity Exploration

Zeqi Zhu, Alberto Garcia-Ortiz, Luc Waeijen, Egor Bondarev, Arash Pourtaherian, Orlando Moreira

ECCV 2024 · Architectures and efficiency › Spiking networks · approach: Event-camera spiking networks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add line-based delta-sigma suppression on top of ReLU (ablation)ELSE · UA-DETRAC SSD-MNV1GMAC: 0.59 -> 0.46Improved
add activation quantization (ablation)ELSE · UA-DETRAC SSD-MNV1GMAC: 0.46 -> 0.34Improved
add event-aware sparsity penalty (ablation)ELSE · UA-DETRAC SSD-MNV1mAP@0.5 change: -0.62%Hurt
add MAC-aware penalty weighting (ablation)ELSE · UA-DETRAC SSD-MNV1GMAC: 0.31 -> 0.23Improved
add line-based penalty (ablation)ELSE · UA-DETRAC SSD-MNV1GMAC: 0.23 -> 0.19Improved
mix ELSE with temporal CATS on memory-heavy layersELSE · UA-DETRAC SSD-MNV1state memory: 20.20 MB -> 9.22 MB vs CATSImproved
mix ELSE with spatial STARELSE · MPII RN50GMAC reduction ratio: 5.75x -> 8.83xImproved
use ELSE alone vs STAR on ResNet-50 pose estimationELSE · MPII RN50GMAC reduction ratio: 6.70x -> 5.75xHurt
mix ELSE with temporal CATS vs full temporal CATS on MNV2-SSDLite computationELSE · UA-DETRAC MNV2-SSDLiteGMAC reduction ratio: 4.51x -> 3.99x with 31.19 MB -> 14.56 MBMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy