Papers › Bag of Tricks for Image Classification with Convolutional Neural Networks
Bag of Tricks for Image Classification with Convolutional Neural Networks
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.
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.
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.
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.
b4e26744ad9e217a · report
b8d5814ad4631b08 · report
82c48515ddda4614 · report
38093779943ae353 · report
de47a57778dd152f · report
e83a42da4ac207cc · report
7d86840aa94ec126 · report
11d835e45631ea6b · report
52a9653519e980d2 · report
f0a6216664197738 · report
237abd0c98440417 · report
c5cd33786bbc32f6 · report
bb26e0be1ece15c0 · report
e60387e9529f63ff · report
1a9d7e65e0a9fbc9 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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