Searching techniques in most of existing neural architecture search (NAS)
algorithms are mainly dominated by differentiable methods for the efficiency
reason. In contrast, we develop an efficient continuous evolutionary approach
for searching neural networks. Architectures in the population that share
parameters within one SuperNet in the latest generation will be tuned over the
training dataset with a few epochs. The searching in the next evolution
generation will directly inherit both the SuperNet and the population, which
accelerates the optimal network generation. The non-dominated sorting strategy
is further applied to preserve only results on the Pareto front for accurately
updating the SuperNet. Several neural networks with different model sizes and
performances will be produced after the continuous search with only 0.4 GPU
days. As a result, our framework provides a series of networks with the number
of parameters ranging from 3.7M to 5.1M under mobile settings. These networks
surpass those produced by the state-of-the-art methods on the benchmark
ImageNet dataset.

本论文提出一种高效的连续演化方法用于搜索神经网络，该方法在优化神经网络的同时，使用优化后的神经网络在下一次的演化中，大大地加速了网络生成的效率。实验表明，该方法产生的神经网络在 mobile 设置下，参数数量在 3.7M 到 5.1M 之间不等，在 ImageNet 数据集上的表现超过了目前已有的先进方法。

CARS：高效神经结构搜索的不间断进化

CARS: Continuous Evolution for Efficient Neural Architecture Search

We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze
its advantages over existing NAS approaches. Existing one-shot method, however,
is hard to train and not yet effective on large scale datasets like ImageNet.
This work propose a Single Path One-Shot model to address the challenge in the
training. Our central idea is to construct a simplified supernet, where all
architectures are single paths so that weight co-adaption problem is
alleviated. Training is performed by uniform path sampling. All architectures
(and their weights) are trained fully and equally.
Comprehensive experiments verify that our approach is flexible and effective.
It is easy to train and fast to search. It effortlessly supports complex search
spaces (e.g., building blocks, channel, mixed-precision quantization) and
different search constraints (e.g., FLOPs, latency). It is thus convenient to
use for various needs. It achieves start-of-the-art performance on the large
dataset ImageNet.

本文介绍了一种使用简化的超网络进行单路径神经架构搜索的方法，该方法易于训练、快速搜索、灵活支持不同的搜索约束，并在大规模数据集 ImageNet 上实现了最先进的性能。

单路径统一采样一次性神经网络结构搜索

Single Path One-Shot Neural Architecture Search with Uniform Sampling

Object detectors are usually equipped with backbone networks designed for
image classification. It might be sub-optimal because of the gap between the
tasks of image classification and object detection. In this work, we present
DetNAS to use Neural Architecture Search (NAS) for the design of better
backbones for object detection. It is non-trivial because detection training
typically needs ImageNet pre-training while NAS systems require accuracies on
the target detection task as supervisory signals. Based on the technique of
one-shot supernet, which contains all possible networks in the search space, we
propose a framework for backbone search on object detection. We train the
supernet under the typical detector training schedule: ImageNet pre-training
and detection fine-tuning. Then, the architecture search is performed on the
trained supernet, using the detection task as the guidance. This framework
makes NAS on backbones very efficient. In experiments, we show the
effectiveness of DetNAS on various detectors, for instance, one-stage RetinaNet
and the two-stage FPN. We empirically find that networks searched on object
detection shows consistent superiority compared to those searched on ImageNet
classification. The resulting architecture achieves superior performance than
hand-crafted networks on COCO with much less FLOPs complexity.

本文提出了一种名为 DetNAS 的方法，使用神经结构搜索技术来设计用于目标检测的骨干网络，实验证明通过 DetNAS 搜索得到的网络在 COCO 数据集上的性能要优于手工设计的网络。