Papers › Fixing the train-test resolution discrepancy

Fixing the train-test resolution discrepancy

14 Jun 2019NeurIPS 2019 12arXiv:1906.06423archive 2025-07-28

Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Hervé Jégou

Data-augmentation is key to the training of neural networks for image classification. This paper first shows that existing augmentations induce a significant discrepancy between the typical size of the objects seen by the classifier at train and test time. We experimentally validate that, for a target test resolution, using a lower train resolution offers better classification at test time. We then propose a simple yet effective and efficient strategy to optimize the classifier performance when the train and test resolutions differ. It involves only a computationally cheap fine-tuning of the network at the test resolution. This enables training strong classifiers using small training images. For instance, we obtain 77.1% top-1 accuracy on ImageNet with a ResNet-50 trained on 128x128 images, and 79.8% with one trained on 224x224 image. In addition, if we use extra training data we get 82.5% with the ResNet-50 train with 224x224 images. Conversely, when training a ResNeXt-101 32x48d pre-trained in weakly-supervised fashion on 940 million public images at resolution 224x224 and further optimizing for test resolution 320x320, we obtain a test top-1 accuracy of 86.4% (top-5: 98.0%) (single-crop). To the best of our knowledge this is the highest ImageNet single-crop, top-1 and top-5 accuracy to date.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 2 code samples harvested from 1 repository linked to this paper: 0 ran · 2 unverified.

By repository: official repository: 2 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

facebookresearch/FixRes officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
kun-woo-park/Deeplearning_project_STL_10 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
libffcv/ffcv-imagenet mentioned on GitHubpytorchApache-2.0Syntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

2 samples harvested: 0 ran · 2 unverified. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2unverified

Licence: 2 of the 2 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 facebookresearch/FixRes. “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 “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

facebookresearch/FixRes official repository 2 samples, 0 ran · 2 unverified
center_crop_new transforms_v2.py unverified licence not identified · pointer only · 6c1d71668610f7e5 · report
crop in 99 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
transforms_v2.py unverified licence not identified · pointer only · 1ab55a62e2b5f143 · report

Tasks

Data AugmentationFine-Grained Image ClassificationGeneral ClassificationImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification Birdsnap FixSENet-154 Accuracy 84.3% #2 of 5 Archive leaderboard report
Fine-Grained Image Classification CUB-200-2011 FixSENet-154 Accuracy 88.7 #19 of 30 Archive leaderboard report
Fine-Grained Image Classification NABirds FixSENet-154 Accuracy 89.2% #20 of 30 Archive leaderboard report
Fine-Grained Image Classification Oxford 102 Flowers FixInceptionResNet-V2 Accuracy 95.7% #20 of 25 Archive leaderboard report
Fine-Grained Image Classification Oxford 102 Flowers FixInceptionResNet-V2 Top-1 Error Rate 4.3% #20 of 25 Archive leaderboard report
Fine-Grained Image Classification Oxford-IIIT Pet Dataset FixSENet-154 Accuracy 94.8% #11 of 15 Archive leaderboard report
Fine-Grained Image Classification Oxford-IIIT Pet Dataset FixSENet-154 Top-1 Error Rate 5.2% #11 of 15 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars FixSENet-154 Accuracy 94.4% #46 of 83 Archive leaderboard report
Image Classification ImageNet FixResNeXt-101 32x48d Hardware Burden 62G #152 of 1060 Archive leaderboard report
Image Classification ImageNet FixResNeXt-101 32x48d Number of params 829M #152 of 1060 Archive leaderboard report
Image Classification ImageNet FixResNeXt-101 32x48d Top 1 Accuracy 86.4% #152 of 1060 Archive leaderboard report
Image Classification ImageNet FixResNeXt-101 32x48d Top 5 Accuracy 98.0% #152 of 1060 Archive leaderboard report
Image Classification ImageNet FixResNet-50 Billion-scale@224 Number of params 25.6M #529 of 1060 Archive leaderboard report
Image Classification ImageNet FixResNet-50 Billion-scale@224 Top 1 Accuracy 82.5% #529 of 1060 Archive leaderboard report
Image Classification ImageNet FixResNet-50 CutMix Top 1 Accuracy 79.8% #734 of 1060 Archive leaderboard report
Image Classification ImageNet FixResNet-50 Top 1 Accuracy 79.1% #777 of 1060 Archive leaderboard report
Image Classification ImageNet ReaL FixResNeXt-101 32x48d Accuracy 89.73% #23 of 57 Archive leaderboard report
Image Classification ImageNet ReaL FixResNeXt-101 32x48d Params 829M #23 of 57 Archive leaderboard report
Image Classification iNaturalist FixSENet-154 Top 1 Accuracy 75.4 #11 of 19 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: FixRes

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockColorJitterConvolutionFixResGlobal Average PoolingGrouped ConvolutionKaiming InitializationMax PoolingRandom Horizontal FlipRandom Resized CropReLUResNeXtResNeXt BlockResidual BlockResidual Connection

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