SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.07636 · 2019

Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Convolutional neural networks (CNNs) introduce state-of-the-art results for various tasks with the price of high computational demands. Inspired by the observation that spatial correlation exists in CNN output feature maps (ofms), we propose a method to dynamically predict whether ofm activations are zero-valued or not according to their neighboring activation values, thereby avoiding zero-valued activations and reducing the number of convolution operations. We implement the zero activation predictor (ZAP) with a lightweight CNN, which imposes negligible overheads and is easy to deploy on existing models. ZAPs are trained by mimicking hidden layer ouputs; thereby, enabling a parallel and label-free training. Furthermore, without retraining, each ZAP can be tuned to a different operating point trading accuracy for MAC reduction.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1909.07636")
get_code_for_paper("1909.07636")
have("1909.07636")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1909.07636.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1909.07636.svg)](https://syntology.ai/paper/1909.07636)

Connect an agent — have() is free.