Evolutionary Neural Cascade Search across Supernetworks

• URL: http://arxiv.org/abs/2203.04011v1
• Date: Tue, 8 Mar 2022 11:06:01 GMT
• Title: Evolutionary Neural Cascade Search across Supernetworks
• Authors: Alexander Chebykin, Tanja Alderliesten, Peter A. N. Bosman
• Abstract summary: We introduce ENCAS - Evolutionary Neural Cascade Search. ENCAS can be used to search over multiple pretrained supernetworks. We test ENCAS on common computer vision benchmarks.
• Score: 68.8204255655161
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: To achieve excellent performance with modern neural networks, having the right network architecture is important. Neural Architecture Search (NAS) concerns the automatic discovery of task-specific network architectures. Modern NAS approaches leverage supernetworks whose subnetworks encode candidate neural network architectures. These subnetworks can be trained simultaneously, removing the need to train each network from scratch, thereby increasing the efficiency of NAS. A recent method called Neural Architecture Transfer (NAT) further improves the efficiency of NAS for computer vision tasks by using a multi-objective evolutionary algorithm to find high-quality subnetworks of a supernetwork pretrained on ImageNet. Building upon NAT, we introduce ENCAS - Evolutionary Neural Cascade Search. ENCAS can be used to search over multiple pretrained supernetworks to achieve a trade-off front of cascades of different neural network architectures, maximizing accuracy while minimizing FLOPS count. We test ENCAS on common computer vision benchmarks (CIFAR-10, CIFAR-100, ImageNet) and achieve Pareto dominance over previous state-of-the-art NAS models up to 1.5 GFLOPS. Additionally, applying ENCAS to a pool of 518 publicly available ImageNet classifiers leads to Pareto dominance in all computation regimes and to increasing the maximum accuracy from 88.6% to 89.0%, accompanied by an 18\% decrease in computation effort from 362 to 296 GFLOPS. Our code is available at https://github.com/AwesomeLemon/ENCAS

Related papers

• DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions [121.05720140641189]
  We develop a family of models with the distilling neural architecture (DNA) techniques. Our proposed DNA models can rate all architecture candidates, as opposed to previous works that can only access a sub- search space using algorithms. Our models achieve state-of-the-art top-1 accuracy of 78.9% and 83.6% on ImageNet for a mobile convolutional network and a small vision transformer, respectively.
  arXiv  Detail & Related papers  (2024-03-02T22:16:47Z)
• NAS-FCOS: Efficient Search for Object Detection Architectures [113.47766862146389]
  We propose an efficient method to obtain better object detectors by searching for the feature pyramid network (FPN) and the prediction head of a simple anchor-free object detector. With carefully designed search space, search algorithms, and strategies for evaluating network quality, we are able to find top-performing detection architectures within 4 days using 8 V100 GPUs.
  arXiv  Detail & Related papers  (2021-10-24T12:20:04Z)
• Learning Versatile Neural Architectures by Propagating Network Codes [74.2450894473073]
  We propose a novel "neural predictor", which is able to predict an architecture's performance in multiple datasets and tasks. NCP learns from network codes but not original data, enabling it to update the architecture efficiently across datasets.
  arXiv  Detail & Related papers  (2021-03-24T15:20:38Z)
• Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective [88.39981851247727]
  We propose a novel framework called training-free neural architecture search (TE-NAS) TE-NAS ranks architectures by analyzing the spectrum of the neural tangent kernel (NTK) and the number of linear regions in the input space. We show that: (1) these two measurements imply the trainability and expressivity of a neural network; (2) they strongly correlate with the network's test accuracy.
  arXiv  Detail & Related papers  (2021-02-23T07:50:44Z)
• FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search [35.61441231491448]
  We propose a Fast Network Adaptation (FNA++) method, which can adapt both the architecture and parameters of a seed network. In our experiments, we apply FNA++ on MobileNetV2 to obtain new networks for semantic segmentation, object detection, and human pose estimation. The total computation cost of FNA++ is significantly less than SOTA segmentation and detection NAS approaches.
  arXiv  Detail & Related papers  (2020-06-21T10:03:34Z)
• Neural Architecture Search without Training [8.067283219068832]
  In this work, we examine the overlap of activations between datapoints in untrained networks. We motivate how this can give a measure which is usefully indicative of a network's trained performance. We incorporate this measure into a simple algorithm that allows us to search for powerful networks without any training in a matter of seconds on a single GPU.
  arXiv  Detail & Related papers  (2020-06-08T14:53:56Z)
• Neural Architecture Transfer [20.86857986471351]
  Existing approaches require one complete search for each deployment specification of hardware or objective. We propose Neural Architecture Transfer (NAT) to overcome this limitation. NAT is designed to efficiently generate task-specific custom models that are competitive under multiple conflicting objectives.
  arXiv  Detail & Related papers  (2020-05-12T15:30:36Z)
• Fast Neural Network Adaptation via Parameter Remapping and Architecture Search [35.61441231491448]
  Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as the backbone. One major challenge though, is that ImageNet pre-training of the search space representation incurs huge computational cost. In this paper, we propose a Fast Neural Network Adaptation (FNA) method, which can adapt both the architecture and parameters of a seed network.
  arXiv  Detail & Related papers  (2020-01-08T13:45:15Z)
• DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning [135.27931587381596]
  We propose an efficient and unified NAS framework termed DDPNAS via dynamic distribution pruning. In particular, we first sample architectures from a joint categorical distribution. Then the search space is dynamically pruned and its distribution is updated every few epochs. With the proposed efficient network generation method, we directly obtain the optimal neural architectures on given constraints.
  arXiv  Detail & Related papers  (2019-05-28T06:35:52Z)

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.