首页/论文/2007.10396

arXiv 2007.103962020-07-20cs.CVcs.LGcs.NE

NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search

Michigan State University（密歇根州立大学）

Zhichao Lu, Kalyanmoy Deb, Erik Goodman, Wolfgang Banzhaf, Vishnu Naresh Boddeti

备注：: Accepted for oral presentation at ECCV 2020

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

In this paper, we propose an efficient NAS algorithm for generating task-specific models that are competitive under multiple competing objectives. It comprises of two surrogates, one at the architecture level to improve sample efficiency and one at the weights level, through a supernet, to improve gradient descent training efficiency. On standard benchmark datasets (C10, C100, ImageNet), the resulting models, dubbed NSGANetV2, either match or outperform models from existing approaches with the search being orders of magnitude more sample efficient. Furthermore, we demonstrate the effectiveness and versatility of the proposed method on six diverse non-standard datasets, e.g. STL-10, Flowers102, Oxford Pets, FGVC Aircrafts etc. In all cases, NSGANetV2s improve the state-of-the-art (under mobile setting), suggesting that NAS can be a viable alternative to conventional transfer learning approaches in handling diverse scenarios such as small-scale or fine-grained datasets. Code is available at https://github.com/mikelzc1990/nsganetv2

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Surrogate-assisted Particle Swarm Optimisation for Evolving Variable-length Transferable Blocks for Image Classification

Victoria University of Wellington（惠灵顿维多利亚大学）

Deep convolutional neural networks have demonstrated promising performance on image classification tasks, but the manual design process becomes more and more complex due to the fast depth growth and the increasingly complex topologies of convolutional neural networks. As a result, neural architecture search has emerged to automatically design convolutional neural networks that outperform handcrafted counterparts. However, the computational cost is immense, e.g. 22,400 GPU-days and 2,000 GPU-days for two outstanding neural architecture search works named NAS and NASNet, respectively, which moti…

2020-07-03cs.CVcs.LGcs.NE

Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation

The architectural advancements in deep neural networks have led to remarkable leap-forwards across a broad array of computer vision tasks. Instead of relying on human expertise, neural architecture search (NAS) has emerged as a promising avenue toward automating the design of architectures. While recent achievements in image classification have suggested opportunities, the promises of NAS have yet to be thoroughly assessed on more challenging tasks of semantic segmentation. The main challenges of applying NAS to semantic segmentation arise from two aspects: (i) high-resolution images to be pro…

2022-08-14cs.CVcs.NE

面向代理辅助神经架构搜索的代码导向语言模型嵌入

Towards Code-Oriented LM Embeddings for Surrogate-Assisted Neural Architecture Search

Georgia Institute of Technology（佐治亚理工学院）；Georgia Tech Research Institute（佐治亚理工研究 institute）

本文提出一种低成本的代码导向语言模型嵌入策略，利用语言模型的归纳偏置，无需微调即可生成高效的架构特征提取器，实验证明其在NAS-Bench-201和einspace搜索空间中优于其他编码方式。

2026-05-15cs.LGcs.NE

神经集成搜索中的代理辅助多样性估计

Surrogate assisted diversity estimation in neural ensemble search

本文针对神经集成搜索（NES）计算成本高的问题，提出双目标代理引导的集成搜索方法，在多个数据集上取得优于或相当于基线的性能。

2026-07-30cs.LG

B2EA: An Evolutionary Algorithm Assisted by Two Bayesian Optimization Modules for Neural Architecture Search

Seoul National University（首尔国立大学）；SK Telecom Co., Ltd.（SK电讯株式会社）

The early pioneering Neural Architecture Search (NAS) works were multi-trial methods applicable to any general search space. The subsequent works took advantage of the early findings and developed weight-sharing methods that assume a structured search space typically with pre-fixed hyperparameters. Despite the amazing computational efficiency of the weight-sharing NAS algorithms, it is becoming apparent that multi-trial NAS algorithms are also needed for identifying very high-performance architectures, especially when exploring a general search space. In this work, we carefully review the late…

2022-02-17cs.LGcs.NE

PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search

RMIT University（皇家墨尔本理工大学）；University of Technology Sydney（悉尼科技大学）

Neural architecture search (NAS) aims to automate architecture engineering in neural networks. This often requires a high computational overhead to evaluate a number of candidate networks from the set of all possible networks in the search space during the search. Prediction of the networks' performance can alleviate this high computational overhead by mitigating the need for evaluating every candidate network. Developing such a predictor typically requires a large number of evaluated architectures which may be difficult to obtain. We address this challenge by proposing a novel evolutionary-ba…

2022-04-27cs.CV

更多相关论文收起更多论文

Bi-fidelity Evolutionary Multiobjective Search for Adversarially Robust Deep Neural Architectures

Deep neural networks have been found vulnerable to adversarial attacks, thus raising potentially concerns in security-sensitive contexts. To address this problem, recent research has investigated the adversarial robustness of deep neural networks from the architectural point of view. However, searching for architectures of deep neural networks is computationally expensive, particularly when coupled with adversarial training process. To meet the above challenge, this paper proposes a bi-fidelity multiobjective neural architecture search approach. First, we formulate the NAS problem for enhancin…

2022-07-12cs.LGcs.NE

用于自由形式超表面设计参数优化的代理辅助扩展生成对抗网络

A Surrogate-Assisted Extended Generative Adversarial Network for Parameter Optimization in Free-Form Metasurface Design

Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（高性能计算研究所（IHPC），新加坡科技研究局（A*STAR））

提出代理辅助的扩展生成对抗网络XGAN，通过引入物理约束从光谱响应准确生成自由形式超表面，在2万个设计实验中达0.9734准确率且速度提升500倍，可推广至多种逆向设计问题。

2023-10-18cs.CVcs.LGeess.IV

Observer variation-aware medical image segmentation by combining deep learning and surrogate-assisted genetic algorithms

Centrum Wiskunde & Informatica（数学与计算机科学中心）；Netherlands eScience Center（荷兰电子科学中心）；Delft University of Technology（代尔夫特理工大学）；Amsterdam UMC, University of Amsterdam（阿姆斯特丹大学医学中心）

There has recently been great progress in automatic segmentation of medical images with deep learning algorithms. In most works observer variation is acknowledged to be a problem as it makes training data heterogeneous but so far no attempts have been made to explicitly capture this variation. Here, we propose an approach capable of mimicking different styles of segmentation, which potentially can improve quality and clinical acceptance of automatic segmentation methods. In this work, instead of training one neural network on all available data, we train several neural networks on subgroups of…

2020-01-23cs.CVcs.LGcs.NE

EvoGAN: An Evolutionary Computation Assisted GAN

East China Normal University（华东师范大学）；University of International Business and Economics（对外经济贸易大学）；Beijing University of Posts and Telecommunications（北京邮电大学）

The image synthesis technique is relatively well established which can generate facial images that are indistinguishable even by human beings. However, all of these approaches uses gradients to condition the output, resulting in the outputting the same image with the same input. Also, they can only generate images with basic expression or mimic an expression instead of generating compound expression. In real life, however, human expressions are of great diversity and complexity. In this paper, we propose an evolutionary algorithm (EA) assisted GAN, named EvoGAN, to generate various compound ex…

2021-10-22cs.AIcs.CVcs.NE

Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution

Tel Aviv University（特拉维夫大学）

A master face is a face image that passes face-based identity-authentication for a large portion of the population. These faces can be used to impersonate, with a high probability of success, any user, without having access to any user-information. We optimize these faces, by using an evolutionary algorithm in the latent embedding space of the StyleGAN face generator. Multiple evolutionary strategies are compared, and we propose a novel approach that employs a neural network in order to direct the search in the direction of promising samples, without adding fitness evaluations. The results we …

2021-08-19cs.CRcs.CVcs.LG

Distribution Learning Based on Evolutionary Algorithm Assisted Deep Neural Networks for Imbalanced Image Classification

Donghua University（东华大学）；Shanghai Jiao Tong University（上海交通大学）

To address the trade-off problem of quality-diversity for the generated images in imbalanced classification tasks, we research on over-sampling based methods at the feature level instead of the data level and focus on searching the latent feature space for optimal distributions. On this basis, we propose an iMproved Estimation Distribution Algorithm based Latent featUre Distribution Evolution (MEDA_LUDE) algorithm, where a joint learning procedure is programmed to make the latent features both optimized and evolved by the deep neural networks and the evolutionary algorithm, respectively. We ex…

2022-07-26cs.AIcs.CV

3D-Assisted Image Feature Synthesis for Novel Views of an Object

Stanford University（斯坦福大学）

Comparing two images in a view-invariant way has been a challenging problem in computer vision for a long time, as visual features are not stable under large view point changes. In this paper, given a single input image of an object, we synthesize new features for other views of the same object. To accomplish this, we introduce an aligned set of 3D models in the same class as the input object image. Each 3D model is represented by a set of views, and we study the correlation of image patches between different views, seeking what we call surrogates --- patches in one view whose feature content …

2014-11-26cs.CV