# Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition

Source: [Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition](<https://www.sota2.com/research/paper/68fa6a981e209131cea2931c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:21:59.075Z

Authors: Ming Lin, Pichao Wang, Zhenhong Sun, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, Rong Jin

Published: 2021-02-01T18:53:40.000Z

## Abstract

Accuracy predictor is a key component in Neural Architecture Search (NAS) for ranking architectures. Building a high-quality accuracy predictor usually costs enormous computation. To address this issue, instead of using an accuracy predictor, we propose a novel zero-shot index dubbed Zen-Score to rank the architectures. The Zen-Score represents the network expressivity and positively correlates with the model accuracy. The calculation of Zen-Score only takes a few forward inferences through a randomly initialized network, without training network parameters. Built upon the Zen-Score, we further propose a new NAS algorithm, termed as Zen-NAS, by maximizing the Zen-Score of the target network under given inference budgets. Within less than half GPU day, Zen-NAS is able to directly search high performance architectures in a data-free style. Comparing with previous NAS methods, the proposed Zen-NAS is magnitude times faster on multiple server-side and mobile-side GPU platforms with state-of-the-art accuracy on ImageNet. Our source code and pre-trained models are released on https://github.com/idstcv/ZenNAS.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on ImageNet-1k (Top-1 Accuracy and Latency)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-top-1-accuracy-and-latency.md>): Image Classification; ImageNet-1K; Top-1 Acc: 83.6.

- [Image Classification on ImageNet 1k (val) (Top-1 Accuracy & GPU Day)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-top-1-accuracy-and-gpu-day.md>): Image Classification; ImageNet-1k (val); Top-1 Acc: 83.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2102.01063>)

[PDF](<https://arxiv.org/pdf/2102.01063.pdf>)

[Implementation](<https://github.com/idstcv/ZenNAS>)