Bag of Tricks for Image Classification with Convolutional Neural Networks

Abstract

Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods. In the literature, however, most refinements are either briefly mentioned as implementation details or only visible in source code. In this paper, we will examine a collection of such refinements and empirically evaluate their impact on the final model accuracy through ablation study. We will show that, by combining these refinements together, we are able to improve various CNN models significantly. For example, we raise ResNet-50's top-1 validation accuracy from 75.3% to 79.29% on ImageNet. We will also demonstrate that improvement on image classification accuracy leads to better transfer learning performance in other application domains such as object detection and semantic segmentation.

Keywords

Computer scienceConvolutional neural networkArtificial intelligenceTransfer of learningContextual image classificationSegmentationCode (set theory)Machine learningPattern recognition (psychology)Image (mathematics)Object detectionDeep learning

Affiliated Institutions

Amazon (United States) US

Related Publications

A ConvNet for the 2020s

Zhuang Liu , Hanzi Mao , Chao-Yuan Wu +3 more

The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification...

2022 2022 IEEE/CVF Conference on Computer ... 5683 citations

FCOS: Fully Convolutional One-Stage Object Detection

Zhi Tian , Chunhua Shen , Hao Chen +1 more

We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all stat...

2019 5672 citations

Object Detection With Deep Learning: A Review

Zhong‐Qiu Zhao , Peng Zheng , Shou-Tao Xu +1 more

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection ...

2019 IEEE Transactions on Neural Networks ... 5019 citations

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Mingxing Tan , Quoc V. Le

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper...

2019 arXiv (Cornell University) 5008 citations

A survey on Image Data Augmentation for Deep Learning

Connor Shorten , Taghi M. Khoshgoftaar

Abstract Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfi...

2019 Journal Of Big Data 11041 citations

Publication Info

Year: 2019
Type: article
Pages: 558-567
Citations: 1478
Access: Closed

External Links

Download PDF (Free) View on DOI.org arXiv Semantic Scholar

Social Impact

Altmetric

Bag of Tricks for Image Classification with Convolutional Neural Networks

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1478

OpenAlex

154

Influential

1067

CrossRef

Cite This

APA Style

                            
                                    Tong He, 
                                
                                    Zhi Zhang, 
                                
                                    Hang Zhang
                                
                                et al.
                            
                            (2019). 
                            Bag of Tricks for Image Classification with Convolutional Neural Networks. 
                            2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
                            
                            , 558-567.
                            https://doi.org/10.1109/cvpr.2019.00065

Identifiers

DOI: 10.1109/cvpr.2019.00065
arXiv: 1812.01187

Data Quality

Data completeness: 84%