Papers › Bag of Tricks for Image Classification with Convolutional Neural Networks

Bag of Tricks for Image Classification with Convolutional Neural Networks

4 Dec 2018CVPR 2019 6arXiv:1812.01187archive 2025-07-28

Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1812.01187")

Code

Syntology Ran 4 of 15 code samples harvested from 4 repositories linked to this paper; 11 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong.

By repository: community (archive-listed): 13 samples from 4 repositories, 2 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

28 repositories listed; official and paper-mentioned ones first.

dmlc/gluon-cv officialmentioned in papertfApache-2.0 report
Dmitrsl/Tools mentioned on GitHub report
Media-Smart/vedaseg mentioned on GitHubpytorch report
PaddlePaddle/PaddleDetection mentioned on GitHubpaddle report
PaddlePaddle/models mentioned on GitHubpaddleApache-2.0 report
PistonY/ResidualAttentionNetwork mentioned on GitHubtfMIT report
TotalVariation/Flattenet mentioned on GitHubpytorchNOASSERTION report
elasticdeeplearning/edl mentioned on GitHubpaddleApache-2.0 report
jameswang287/Car-Detection mentioned on GitHubpytorch report
paddlepaddle/edl mentioned on GitHubpaddleApache-2.0 report
pshashk/seesaw-facenet mentioned on GitHubpytorch report
qingyuanchen1997/Bag-of-Tricks mentioned on GitHubpytorchMIT report
rwightman/pytorch-image-models mentioned on GitHubpytorch report
seominseok0429/pytorch-warmup-cosine-lr mentioned on GitHubpytorch report
smilingwolf/sw-cv-modelzoo mentioned on GitHubtf report
tyohei/chainerkfac mentioned on GitHub report
yangyucheng000/resnet_Ascend mentioned on GitHubmindsporeApache-2.0 report
PaddlePaddle/PaddleClas paddleApache-2.0 report
PaddlePaddle/PaddleOCR paddleApache-2.0 report
open-mmlab/mmpose pytorchApache-2.0 report
yangyucheng000/resnet_GPU mindsporeApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested; 4 ran; 2 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
11unverified

Licence: 5 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

extract tyohei/chainerkfac/chainerkfac/optimizers/kfac.py community (archive-listed) ran · our draft was wrong MIT (permissive) · b4e26744ad9e217a · report
get_dict_key cinastanbean/Pytorch-Multi-Task-Multi-class-Classification/src/main_mtmc_resnet.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · b8d5814ad4631b08 · report
calculate_gain yangyucheng000/resnet_Ascend/src/resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · 82c48515ddda4614 · report
cout_confmatrix_tofile cinastanbean/Pytorch-Multi-Task-Multi-class-Classification/src/main_mtmc_resnet.py community (archive-listed) unverified no licence file found · pointer only · 38093779943ae353 · report
cutout PistonY/ResidualAttentionNetwork/lib/piston_util.py community (archive-listed) unverified MIT (permissive) · de47a57778dd152f · report
format_time PistonY/ResidualAttentionNetwork/lib/piston_util.py community (archive-listed) unverified MIT (permissive) · e83a42da4ac207cc · report
get_ems PistonY/ResidualAttentionNetwork/kaggle/utils.py community (archive-listed) unverified MIT (permissive) · 7d86840aa94ec126 · report
get_liner_lr yangyucheng000/resnet_Ascend/gpu_resnet_benchmark.py community (archive-listed) unverified Apache-2.0 (permissive) · 11d835e45631ea6b · report
get_top5_acc yangyucheng000/resnet_Ascend/postprocess.py community (archive-listed) unverified Apache-2.0 (permissive) · 52a9653519e980d2 · report
kaiming_normal yangyucheng000/resnet_Ascend/src/resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · f0a6216664197738 · report
rescale PistonY/ResidualAttentionNetwork/lib/piston_util.py community (archive-listed) unverified MIT (permissive) · 237abd0c98440417 · report
show_predict_info yangyucheng000/resnet_Ascend/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · c5cd33786bbc32f6 · report
slmc_validate cinastanbean/Pytorch-Multi-Task-Multi-class-Classification/src/main_mtmc_resnet.py community (archive-listed) unverified no licence file found · pointer only · bb26e0be1ece15c0 · report
round_filters identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · e60387e9529f63ff · report
round_repeats identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · 1a9d7e65e0a9fbc9 · report

Tasks

Domain GeneralizationGeneral ClassificationImage ClassificationObject DetectionSemantic SegmentationTransfer Learningimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization VizWiz-Classification ResNet-26-D Accuracy - All Images 39.7 #38 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification ResNet-26-D Accuracy - Clean Images 43.5 #38 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification ResNet-26-D Accuracy - Corrupted Images 35.8 #38 of 90 Archive leaderboard report
Image Classification ImageNet ResNet-50-D Number of params 25M #883 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-50-D Top 1 Accuracy 77.16% #883 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: ResNet-D

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionCosine AnnealingGlobal Average PoolingLabel SmoothingMax PoolingMixupNesterov Accelerated GradientRandom Horizontal FlipRandom Resized CropReLUResNet-DResidual BlockResidual ConnectionWeight DecayXavier Initialization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections