AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Can we get the best of both Binary Neural Networks and Spiking Neural Networks for Efficient Computer Vision?

Gourav Datta, Zeyu Liu, Peter Anthony Beerel

ICLR 2024 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Combines binary neural networks and spiking neural networks to get sparse, binary-operation vision models for efficient computer vision.

Problem

BNNs lack activation sparsity and still need many non-binary operations, while SNNs provide sparsity; the paper targets efficient low-power vision by combining the two.

Approach

Unifies binary and spiking paradigms so the network has both binary weights/activations and spike-driven sparsity, aiming to get the efficiency benefits of both.

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