SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.00177 · 2021

Greedy Network Enlarging

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

Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i.e., models with more MACs typically achieve better accuracy, such as EfficientNet and RegNet. These works try to enlarge all the stages in the model with one unified rule by sampling and statistical methods. However, we observe that some network architectures have similar MACs and accuracies, but their allocations on computations for different stages are quite different. In this paper, we propose to enlarge the capacity of CNN models by improving their width, depth and resolution on stage level. Under the assumption that the top-performing smaller CNNs are a proper subcomponent of the top-performing larger CNNs, we propose an greedy network enlarging method based on the reallocation of computations. With step-by-step modifying the computations on different stages, the enlarged network will be equipped with optimal allocation and utilization of MACs. On EfficientNet, our method consistently outperforms the performance of the original scaling method. In particular, with application of our method on GhostNet, we achieve state-of-the-art 80.9% and 84.3% ImageNet top-1 accuracies under the setting of 600M and 4.4B MACs, respectively.

For agents

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

get_harvested_code_for_paper("2108.00177")
get_code_for_paper("2108.00177")
have("2108.00177")

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

curl https://syntology.ai/api/ran/2108.00177.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.00177.svg)](https://syntology.ai/paper/2108.00177)

Connect an agent — have() is free.