Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network

Abstract

Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs). However, attempts to combine existing techniques to create a practical model are still uncommon. In this study, we carry out extensive experiments to validate that carefully assembling these techniques and applying them to basic CNN models (e.g. ResNet and MobileNet) can improve the accuracy and robustness of the models while minimizing the loss of throughput. Our proposed assembled ResNet-50 shows improvements in top-1 accuracy from 76.3\% to 82.78\%, mCE from 76.0\% to 48.9\% and mFR from 57.7\% to 32.3\% on ILSVRC2012 validation set. With these improvements, inference throughput only decreases from 536 to 312. To verify the performance improvement in transfer learning, fine grained classification and image retrieval tasks were tested on several public datasets and showed that the improvement to backbone network performance boosted transfer learning performance significantly. Our approach achieved 1st place in the iFood Competition Fine-Grained Visual Recognition at CVPR 2019, and the source code and trained models are available at https://github.com/clovaai/assembled-cnn

9 pages, 2 figures, 18 tables

References in corpus (13)

• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• mixup: Beyond Empirical Risk Minimization
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Fine-Grained Visual Classification of Aircraft
• Mixed Precision Training
• AutoAugment: Learning Augmentation Policies from Data
• DropBlock: A regularization method for convolutional networks
• Regularizing Neural Networks by Penalizing Confident Output Distributions
• Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition
• Adversarial Examples Improve Image Recognition

Cited by in corpus (14)

• Improving robustness against common corruptions by covariate shift adaptation
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift
• Are we done with ImageNet?
• LambdaNetworks: Modeling Long-Range Interactions Without Attention
• ResNet strikes back: An improved training procedure in timm
• HCM: Hardware-Aware Complexity Metric for Neural Network Architectures
• On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness
• A linearized framework and a new benchmark for model selection for fine-tuning
• Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training
• Curriculum By Smoothing
• ImageNet-21K Pretraining for the Masses
• Defending Against Image Corruptions Through Adversarial Augmentations
• Sequential Random Network for Fine-grained Image Classification
• Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs