Stage-Wise Neural Architecture Search
- URL: http://arxiv.org/abs/2004.11178v2
- Date: Mon, 19 Oct 2020 21:59:00 GMT
- Title: Stage-Wise Neural Architecture Search
- Authors: Artur Jordao, Fernando Akio, Maiko Lie and William Robson Schwartz
- Abstract summary: Modern convolutional networks such as ResNet and NASNet have achieved state-of-the-art results in many computer vision applications.
These networks consist of stages, which are sets of layers that operate on representations in the same resolution.
It has been demonstrated that increasing the number of layers in each stage improves the prediction ability of the network.
However, the resulting architecture becomes computationally expensive in terms of floating point operations, memory requirements and inference time.
- Score: 65.03109178056937
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Modern convolutional networks such as ResNet and NASNet have achieved
state-of-the-art results in many computer vision applications. These
architectures consist of stages, which are sets of layers that operate on
representations in the same resolution. It has been demonstrated that
increasing the number of layers in each stage improves the prediction ability
of the network. However, the resulting architecture becomes computationally
expensive in terms of floating point operations, memory requirements and
inference time. Thus, significant human effort is necessary to evaluate
different trade-offs between depth and performance. To handle this problem,
recent works have proposed to automatically design high-performance
architectures, mainly by means of neural architecture search (NAS). Current NAS
strategies analyze a large set of possible candidate architectures and, hence,
require vast computational resources and take many GPUs days. Motivated by
this, we propose a NAS approach to efficiently design accurate and low-cost
convolutional architectures and demonstrate that an efficient strategy for
designing these architectures is to learn the depth stage-by-stage. For this
purpose, our approach increases depth incrementally in each stage taking into
account its importance, such that stages with low importance are kept shallow
while stages with high importance become deeper. We conduct experiments on the
CIFAR and different versions of ImageNet datasets, where we show that
architectures discovered by our approach achieve better accuracy and efficiency
than human-designed architectures. Additionally, we show that architectures
discovered on CIFAR-10 can be successfully transferred to large datasets.
Compared to previous NAS approaches, our method is substantially more
efficient, as it evaluates one order of magnitude fewer models and yields
architectures on par with the state-of-the-art.
Related papers
- EM-DARTS: Hierarchical Differentiable Architecture Search for Eye Movement Recognition [54.99121380536659]
Eye movement biometrics have received increasing attention thanks to its high secure identification.
Deep learning (DL) models have been recently successfully applied for eye movement recognition.
DL architecture still is determined by human prior knowledge.
We propose EM-DARTS, a hierarchical differentiable architecture search algorithm to automatically design the DL architecture for eye movement recognition.
arXiv Detail & Related papers (2024-09-22T13:11:08Z) - Efficient Search of Multiple Neural Architectures with Different
Complexities via Importance Sampling [3.759936323189417]
This study focuses on the architecture complexity-aware one-shot NAS that optimize the objective function composed of the weighted sum of two metrics.
The proposed method is applied to the architecture search of convolutional neural networks on the CIAFR-10 and ImageNet datasets.
arXiv Detail & Related papers (2022-07-21T07:06:03Z) - SuperNet in Neural Architecture Search: A Taxonomic Survey [14.037182039950505]
This survey focuses on the supernet optimization that builds a neural network that assembles all the architectures as its sub models by using weight sharing.
We aim to accomplish that by proposing them as solutions to the common challenges found in the literature: data-side optimization, poor rank correlation alleviation, and transferable NAS for a number of deployment scenarios.
arXiv Detail & Related papers (2022-04-08T08:29:52Z) - Rethinking Architecture Selection in Differentiable NAS [74.61723678821049]
Differentiable Neural Architecture Search is one of the most popular NAS methods for its search efficiency and simplicity.
We propose an alternative perturbation-based architecture selection that directly measures each operation's influence on the supernet.
We find that several failure modes of DARTS can be greatly alleviated with the proposed selection method.
arXiv Detail & Related papers (2021-08-10T00:53:39Z) - Operation Embeddings for Neural Architecture Search [15.033712726016255]
We propose the replacement of fixed operator encoding with learnable representations in the optimization process.
Our method produces top-performing architectures that share similar operation and graph patterns.
arXiv Detail & Related papers (2021-05-11T09:17:10Z) - Weak NAS Predictors Are All You Need [91.11570424233709]
Recent predictor-based NAS approaches attempt to solve the problem with two key steps: sampling some architecture-performance pairs and fitting a proxy accuracy predictor.
We shift the paradigm from finding a complicated predictor that covers the whole architecture space to a set of weaker predictors that progressively move towards the high-performance sub-space.
Our method costs fewer samples to find the top-performance architectures on NAS-Bench-101 and NAS-Bench-201, and it achieves the state-of-the-art ImageNet performance on the NASNet search space.
arXiv Detail & Related papers (2021-02-21T01:58:43Z) - Hierarchical Neural Architecture Search for Deep Stereo Matching [131.94481111956853]
We propose the first end-to-end hierarchical NAS framework for deep stereo matching.
Our framework incorporates task-specific human knowledge into the neural architecture search framework.
It is ranked at the top 1 accuracy on KITTI stereo 2012, 2015 and Middlebury benchmarks, as well as the top 1 on SceneFlow dataset.
arXiv Detail & Related papers (2020-10-26T11:57:37Z) - Interpretable Neural Architecture Search via Bayesian Optimisation with
Weisfeiler-Lehman Kernels [17.945881805452288]
Current neural architecture search (NAS) strategies focus on finding a single, good, architecture.
We propose a Bayesian optimisation approach for NAS that combines the Weisfeiler-Lehman graph kernel with a Gaussian process surrogate.
Our method affords interpretability by discovering useful network features and their corresponding impact on the network performance.
arXiv Detail & Related papers (2020-06-13T04:10:34Z) - A Semi-Supervised Assessor of Neural Architectures [157.76189339451565]
We employ an auto-encoder to discover meaningful representations of neural architectures.
A graph convolutional neural network is introduced to predict the performance of architectures.
arXiv Detail & Related papers (2020-05-14T09:02:33Z) - DCNAS: Densely Connected Neural Architecture Search for Semantic Image
Segmentation [44.46852065566759]
We propose a Densely Connected NAS (DCNAS) framework, which directly searches the optimal network structures for the multi-scale representations of visual information.
Specifically, by connecting cells with each other using learnable weights, we introduce a densely connected search space to cover an abundance of mainstream network designs.
We demonstrate that the architecture obtained from our DCNAS algorithm achieves state-of-the-art performances on public semantic image segmentation benchmarks.
arXiv Detail & Related papers (2020-03-26T13:21:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.