Neural Architecture Search for Lightweight Non-Local Networks

By Yingwei Li, Xiaojie Jin, Jieru Mei, Xiaochen Lian, Linjie Yang, Cihang Xie, Qihang Yu, Yuyin Zhou, Song Bai, Alan L. Yuille. 2020

55 citations recorded by the source corpus.

Non-Local (NL) blocks have been widely studied in various vision tasks. However, it has been rarely explored to embed the NL blocks in mobile neural networks, mainly due to the following challenges: 1) NL blocks generally have heavy computation cost which makes it difficult to be applied in applications where computational resources are limited, and 2) it is an open problem to discover an optimal configuration to embed NL blocks into mobile neural networks. We propose AutoNL to overcome the above two obstacles. Firstly, we propose a Lightweight Non-Local (LightNL) block by squeezing the transformation operations and incorporating compact features. With the novel design choices, the proposed LightNL block is 400 times computationally cheaper} than its conventional counterpart without sacrificing the performance. Secondly, by relaxing the structure of the LightNL block to be differentiable during training, we propose an efficient neural architecture search algorithm to learn an optimal configuration of LightNL blocks in an end-to-end manner. Notably, using only 32 GPU hours, the searched AutoNL model achieves 77.7% top-1 accuracy on ImageNet under a typical mobile setting (350M FLOPs), significantly outperforming previous mobile models including MobileNetV2 (+5.7%), FBNet (+2.8%) and MnasNet (+2.1%). Code and models are available at https://github.com/LiYingwei/AutoNL.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Neurology, Model Architectures, Neural Architecture Search & AutoML

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Neurology

In Model Architectures

In Neural Architecture Search & AutoML

Citations in the corpus

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation (2020, methodology): “Efficient attention methods are proposed to reduce its complexity [76,42,56].”
GhostNetV2: Enhance Cheap Operation with Long-Range Attention (2022, methodology): “Until now, GhostNet has been the SOTA light-weight model with a good trade-off between accuracy and speed.”
k-means Mask Transformer (2022, background): “Both approaches have boosted various vision tasks, such as image classiﬁcation [19,7,81,44,64,94,32,70,107,103], image generation [78,42], object detection [97,84,81,43,10,116], video recognition [97,19,3,33], semantic segmentation [17,110,46,35,117,115,111,100,11], and panoptic segmentation [94].”