{"url":"/method/fixres","slug":"fixres","name":"FixRes","full_name":"FixRes","full_name_withheld":false,"description_markdown":"**FixRes** is an image scaling strategy that seeks to optimize classifier performance. It is motivated by the observation that data augmentations induce a significant discrepancy between the size of the objects seen by the classifier at train and test time: in fact, a lower train resolution improves the classification at test time! FixRes is a simple strategy to optimize the classifier performance, that employs different train and test resolutions. The calibrations are: (a) calibrating the object sizes by adjusting the crop size and (b) adjusting statistics before spatial pooling.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Fixing the train-test resolution discrepancy","paper":"/paper/fixing-the-train-test-resolution-discrepancy","first_author":"Hugo Touvron","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/fixing-the-train-test-resolution-discrepancy"},"source":{"url":"https://arxiv.org/abs/1906.06423v4","title":"Fixing the train-test resolution discrepancy","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Scaling Strategies","url":"/methods/category/image-scaling-strategies","pwc_aliases":[]}],"n_papers_tagged":10,"archive_num_papers":10,"papers_newest_first":[{"paper":"/paper/deit-iii-revenge-of-the-vit","title":"DeiT III: Revenge of the ViT","date":"2022-04-14","arxiv_id":"2204.07118","n_code_links":12,"syntology":null},{"paper":"/paper/three-things-everyone-should-know-about","title":"Three things everyone should know about Vision Transformers","date":"2022-03-18","arxiv_id":"2203.09795","n_code_links":8,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":0}},{"paper":"/paper/training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","arxiv_id":"2012.12877","n_code_links":40,"syntology":{"ran":12,"of":19,"unverified":7,"pointer_only":3}},{"paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","arxiv_id":"2010.11929","n_code_links":158,"syntology":{"ran":281,"of":419,"unverified":138,"pointer_only":154}},{"paper":"/paper/circumventing-outliers-of-autoaugment-with","title":"Circumventing Outliers of AutoAugment with Knowledge Distillation","date":"2020-03-25","arxiv_id":"2003.11342","n_code_links":1,"syntology":null},{"paper":"/paper/fixing-the-train-test-resolution-discrepancy-2","title":"Fixing the train-test resolution discrepancy: FixEfficientNet","date":"2020-03-18","arxiv_id":"2003.08237","n_code_links":1,"syntology":null},{"paper":"/paper/maxup-a-simple-way-to-improve-generalization","title":"MaxUp: A Simple Way to Improve Generalization of Neural Network Training","date":"2020-02-20","arxiv_id":"2002.09024","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}},{"paper":"/paper/large-scale-learning-of-general-visual","title":"Big Transfer (BiT): General Visual Representation Learning","date":"2019-12-24","arxiv_id":"1912.11370","n_code_links":9,"syntology":{"ran":3,"of":10,"unverified":7,"pointer_only":0}},{"paper":"/paper/self-training-with-noisy-student-improves","title":"Self-training with Noisy Student improves ImageNet classification","date":"2019-11-11","arxiv_id":"1911.04252","n_code_links":13,"syntology":{"ran":5,"of":24,"unverified":19,"pointer_only":0}},{"paper":"/paper/fixing-the-train-test-resolution-discrepancy","title":"Fixing the train-test resolution discrepancy","date":"2019-06-14","arxiv_id":"1906.06423","n_code_links":3,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":2}}],"papers_shown":10,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":9},{"task":"/task/image-classification","name":"image-classification","papers":7},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":5},{"task":"/task/fine-grained-image-classification","name":"Fine-Grained Image Classification","papers":4},{"task":"/task/classification","name":"General Classification","papers":4},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/document-image-classification","name":"Document Image Classification","papers":1},{"task":"/task/document-layout-analysis","name":"Document Layout Analysis","papers":1},{"task":"/task/efficient-vits","name":"Efficient ViTs","papers":1},{"task":"/task/few-shot-image-classification","name":"Few-Shot Image Classification","papers":1},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":1},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/out-of-distribution-generalization","name":"Out-of-Distribution Generalization","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1}],"tasks_shown":18,"n_tasks":18,"usage_by_year":[{"year":"2019","papers":3},{"year":"2020","papers":5},{"year":"2022","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/fixres"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}