Rethinking Channel Dimensions for Efficient Model Design
arXiv:2007.00992
Abstract
Designing an efficient model within the limited computational cost is challenging. We argue the accuracy of a lightweight model has been further limited by the design convention: a stage-wise configuration of the channel dimensions, which looks like a piecewise linear function of the network stage. In this paper, we study an effective channel dimension configuration towards better performance than the convention. To this end, we empirically study how to design a single layer properly by analyzing the rank of the output feature. We then investigate the channel configuration of a model by searching network architectures concerning the channel configuration under the computational cost restriction. Based on the investigation, we propose a simple yet effective channel configuration that can be parameterized by the layer index. As a result, our proposed model following the channel parameterization achieves remarkable performance on ImageNet classification and transfer learning tasks including COCO object detection, COCO instance segmentation, and fine-grained classifications. Code and ImageNet pretrained models are available at https://github.com/clovaai/rexnet.
arXiv comment13 pages, 8 figures, CVPR 2021
References in corpus (20)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- YOLOv3: An Incremental Improvement
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Gaussian Error Linear Units (GELUs)
- In Defense of the Triplet Loss for Person Re-Identification
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- DARTS: Differentiable Architecture Search
- Fine-Grained Visual Classification of Aircraft
- cuDNN: Efficient Primitives for Deep Learning
- Searching for Activation Functions
- MixConv: Mixed Depthwise Convolutional Kernels
- Deep Networks with Stochastic Depth
- DARTS+: Improved Differentiable Architecture Search with Early Stopping
- NSML: Meet the MLaaS platform with a real-world case study
- Pelee: A Real-Time Object Detection System on Mobile Devices
- Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
- AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights