MicroNet: Improving Image Recognition with Extremely Low FLOPs

• URL: http://arxiv.org/abs/2108.05894v1
• Date: Thu, 12 Aug 2021 17:59:41 GMT
• Title: MicroNet: Improving Image Recognition with Extremely Low FLOPs
• Authors: Yunsheng Li and Yinpeng Chen and Xiyang Dai and Dongdong Chen and Mengchen Liu and Lu Yuan and Zicheng Liu and Lei Zhang and Nuno Vasconcelos
• Abstract summary: We find two factors, sparse connectivity and dynamic activation function, are effective to improve the accuracy. We present a new dynamic activation function, named Dynamic Shift Max, to improve the non-linearity. We arrive at a family of networks, named MicroNet, that achieves significant performance gains over the state of the art in the low FLOP regime.
• Score: 82.54764264255505
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e.g. 5M FLOPs on ImageNet classification). We found that two factors, sparse connectivity and dynamic activation function, are effective to improve the accuracy. The former avoids the significant reduction of network width, while the latter mitigates the detriment of reduction in network depth. Technically, we propose micro-factorized convolution, which factorizes a convolution matrix into low rank matrices, to integrate sparse connectivity into convolution. We also present a new dynamic activation function, named Dynamic Shift Max, to improve the non-linearity via maxing out multiple dynamic fusions between an input feature map and its circular channel shift. Building upon these two new operators, we arrive at a family of networks, named MicroNet, that achieves significant performance gains over the state of the art in the low FLOP regime. For instance, under the constraint of 12M FLOPs, MicroNet achieves 59.4\% top-1 accuracy on ImageNet classification, outperforming MobileNetV3 by 9.6\%. Source code is at \href{https://github.com/liyunsheng13/micronet}{https://github.com/liyunsheng13/micronet}.

Related papers

• Learning Activation Functions for Sparse Neural Networks [12.234742322758418]
  Sparse Neural Networks (SNNs) can potentially demonstrate similar performance to their dense counterparts. However, the accuracy drop incurred by SNNs, especially at high pruning ratios, can be an issue in critical deployment conditions. We focus on learning a novel way to tune activation functions for sparse networks.
  arXiv  Detail & Related papers  (2023-05-18T13:30:29Z)
• Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming [15.458305667190256]
  We propose a novel depth compression algorithm which targets general convolution operations. We achieve $1.41times$ speed-up with $0.11%p accuracy gain in MobileNetV2-1.0 on the ImageNet.
  arXiv  Detail & Related papers  (2023-01-28T13:08:54Z)
• MogaNet: Multi-order Gated Aggregation Network [64.16774341908365]
  We propose a new family of modern ConvNets, dubbed MogaNet, for discriminative visual representation learning. MogaNet encapsulates conceptually simple yet effective convolutions and gated aggregation into a compact module. MogaNet exhibits great scalability, impressive efficiency of parameters, and competitive performance compared to state-of-the-art ViTs and ConvNets on ImageNet.
  arXiv  Detail & Related papers  (2022-11-07T04:31:17Z)
• RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network [3.54359747576165]
  RevSilo is the first reversible multi-scale feature fusion module. We create RevBiFPN, a fully reversible bidirectional feature pyramid network. RevBiFPN provides up to a 2.5% boost in AP over HRNet using fewer MACs and a 2.4x reduction in training-time memory.
  arXiv  Detail & Related papers  (2022-06-28T15:48:05Z)
• EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications [68.35683849098105]
  We introduce split depth-wise transpose attention (SDTA) encoder that splits input tensors into multiple channel groups. Our EdgeNeXt model with 1.3M parameters achieves 71.2% top-1 accuracy on ImageNet-1K. Our EdgeNeXt model with 5.6M parameters achieves 79.4% top-1 accuracy on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-06-21T17:59:56Z)
• DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers [105.74546828182834]
  We show a hardware-efficient dynamic inference regime, named dynamic weight slicing, which adaptively slice a part of network parameters for inputs with diverse difficulty levels. We present dynamic slimmable network (DS-Net) and dynamic slice-able network (DS-Net++) by input-dependently adjusting filter numbers of CNNs and multiple dimensions in both CNNs and transformers.
  arXiv  Detail & Related papers  (2021-09-21T09:57:21Z)
• MicroNet: Towards Image Recognition with Extremely Low FLOPs [117.96848315180407]
  MicroNet is an efficient convolutional neural network using extremely low computational cost. A family of MicroNets achieve a significant performance gain over the state-of-the-art in the low FLOP regime. For instance, MicroNet-M1 achieves 61.1% top-1 accuracy on ImageNet classification with 12 MFLOPs, outperforming MobileNetV3 by 11.3%.
  arXiv  Detail & Related papers  (2020-11-24T18:59:39Z)
• Efficient Integer-Arithmetic-Only Convolutional Neural Networks [87.01739569518513]
  We replace conventional ReLU with Bounded ReLU and find that the decline is due to activation quantization. Our integer networks achieve equivalent performance as the corresponding FPN networks, but have only 1/4 memory cost and run 2x faster on modern GPU.
  arXiv  Detail & Related papers  (2020-06-21T08:23:03Z)
• DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks [16.169176006544436]
  We propose a novel dynamic convolution method to adaptively generate convolution kernels based on image contents. Based on the architecture MobileNetV3-Small/Large, DyNet achieves 70.3/77.1% Top-1 accuracy on ImageNet with an improvement of 2.9/1.9%.
  arXiv  Detail & Related papers  (2020-04-22T16:58:05Z)

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.