{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fixing-the-train-test-resolution-discrepancy","title":"Fixing the train-test resolution discrepancy","arxiv_id":"1906.06423","date":"2019-06-14","proceeding":"NeurIPS 2019 12","authors":["Hugo Touvron","Andrea Vedaldi","Matthijs Douze","Hervé Jégou"],"abstract":"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.","url_abs":"https://arxiv.org/abs/1906.06423v4","url_pdf":"https://arxiv.org/pdf/1906.06423v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fixing-the-train-test-resolution-discrepancy","repo_url":"https://github.com/facebookresearch/FixRes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fixing-the-train-test-resolution-discrepancy","repo_url":"https://github.com/kun-woo-park/Deeplearning_project_STL_10","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fixing-the-train-test-resolution-discrepancy","repo_url":"https://github.com/libffcv/ffcv-imagenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"colorjitter","method_name":"ColorJitter"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fixres","method_name":"FixRes"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"resnext","method_name":"ResNeXt"},{"method_slug":"resnext-block","method_name":"ResNeXt Block"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[{"slug":"fixres","name":"FixRes","full_name":"FixRes"}],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-birdsnap","task":"Fine-Grained Image Classification","dataset":"Birdsnap","model":"FixSENet-154","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"84.3%"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-cub-200-1","task":"Fine-Grained Image Classification","dataset":"CUB-200-2011","model":"FixSENet-154","rank_in_archive_order":19,"of":30,"metrics":{"Accuracy":"88.7"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-nabirds","task":"Fine-Grained Image Classification","dataset":"NABirds","model":"FixSENet-154","rank_in_archive_order":20,"of":30,"metrics":{"Accuracy":"89.2%"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford","task":"Fine-Grained Image Classification","dataset":"Oxford 102 Flowers","model":"FixInceptionResNet-V2","rank_in_archive_order":20,"of":25,"metrics":{"Accuracy":"95.7%","Top-1 Error Rate":"4.3%"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford-1","task":"Fine-Grained Image Classification","dataset":"Oxford-IIIT Pet Dataset","model":"FixSENet-154","rank_in_archive_order":11,"of":15,"metrics":{"Accuracy":"94.8%","Top-1 Error Rate":"5.2%"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"FixSENet-154","rank_in_archive_order":46,"of":83,"metrics":{"Accuracy":"94.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"FixResNeXt-101 32x48d","rank_in_archive_order":152,"of":1060,"metrics":{"Hardware Burden":"62G","Number of params":"829M","Top 1 Accuracy":"86.4%","Top 5 Accuracy":"98.0%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"FixResNet-50 Billion-scale@224","rank_in_archive_order":529,"of":1060,"metrics":{"Number of params":"25.6M","Top 1 Accuracy":"82.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"FixResNet-50 CutMix","rank_in_archive_order":734,"of":1060,"metrics":{"Top 1 Accuracy":"79.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"FixResNet-50","rank_in_archive_order":777,"of":1060,"metrics":{"Top 1 Accuracy":"79.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-real","task":"Image Classification","dataset":"ImageNet ReaL","model":"FixResNeXt-101 32x48d","rank_in_archive_order":23,"of":57,"metrics":{"Accuracy":"89.73%","Params":"829M"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist","task":"Image Classification","dataset":"iNaturalist","model":"FixSENet-154","rank_in_archive_order":11,"of":19,"metrics":{"Top 1 Accuracy":"75.4"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.06423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.06423"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/FixRes","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/libffcv/ffcv-imagenet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kun-woo-park/Deeplearning_project_STL_10","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"6c1d71668610f7e5","entry":"center_crop_new","repo":"facebookresearch/FixRes","repo_kind":"official","path":"transforms_v2.py","file_url":"https://github.com/facebookresearch/FixRes/blob/HEAD/transforms_v2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6c1d71668610f7e5"}},{"code_sha256_prefix":"1ab55a62e2b5f143","entry":"crop","repo":"facebookresearch/FixRes","repo_kind":"official","path":"transforms_v2.py","file_url":"https://github.com/facebookresearch/FixRes/blob/HEAD/transforms_v2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1ab55a62e2b5f143"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}