mlsanityData to 7 Oct 2026

Bag of Tricks for Image Classification with Convolutional Neural Networks

arXiv 1812.01187 ↗First posted 4 Dec 2018cs.CVcited by 430

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 430 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 117; 2022: 108; 2023: 79; 2024: 59; 2025: 36; 2026: 31.

430 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  3. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  4. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  5. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  6. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  7. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 390
  8. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  9. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  10. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  11. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  12. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
38 more
  1. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  2. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 251
  3. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  4. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  5. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  6. 2021Learning N:M Fine-grained Structured Sparse Neural Networks From Scratchcited by 177
  7. 2021SSAST: Self-Supervised Audio Spectrogram Transformercited by 166
  8. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
  9. 2021VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examplescited by 154
  10. 2021All Tokens Matter: Token Labeling for Training Better Vision Transformerscited by 144
  11. 2022Understanding The Robustness in Vision Transformerscited by 144
  12. 2023Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspectivecited by 136
  13. 2021MoViNets: Mobile Video Networks for Efficient Video Recognitioncited by 135
  14. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priorscited by 135
  15. 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
  16. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  17. 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
  18. 2021Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognitioncited by 103
  19. 2021Contextual Transformer Networks for Visual Recognitioncited by 90
  20. 2021StrucTexT: Structured Text Understanding with Multi-Modal Transformerscited by 90
  21. 2023DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attentioncited by 90
  22. 2021Characterizing signal propagation to close the performance gap in unnormalized ResNetscited by 87
  23. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
  24. 2022CenterCLIP: Token Clustering for Efficient Text-Video Retrievalcited by 86
  25. 2023Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Modelscited by 86
  26. 2023Curricular Contrastive Regularization for Physics-aware Single Image Dehazingcited by 83
  27. 2022Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognitioncited by 81
  28. 2021Self-supervised representation learning from 12-lead ECG datacited by 80
  29. 2021Advancing Spiking Neural Networks towards Deep Residual Learningcited by 76
  30. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  31. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  32. 2021Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Datacited by 69
  33. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  34. 2023A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scalecited by 69
  35. 2022Corrupted Image Modeling for Self-Supervised Visual Pre-Trainingcited by 68
  36. 2021Stochastic Training is Not Necessary for Generalizationcited by 63
  37. 2021Are we ready for a new paradigm shift? A Survey on Visual Deep MLPcited by 63
  38. 2022Assessing the State of Self-Supervised Human Activity Recognition using Wearablescited by 63

50 most cited of 430 All 430 (JSON)