{"id": 1012323, "name": "Top-1 accuracy", "unit": "%", "createdAt": "2025-02-17T13:09:24.000Z", "updatedAt": "2025-04-22T21:23:29.000Z", "coverage": "", "timespan": "", "datasetId": 6945, "shortUnit": "%", "columnOrder": 0, "shortName": "top_1_accuracy", "catalogPath": "grapher/artificial_intelligence/2025-02-17/papers_with_code_imagenet/papers_with_code_imagenet#top_1_accuracy", "type": "float", "dataChecksum": "12502776186682727139", "metadataChecksum": "-7513347362122027815", "datasetName": "AI Performance on Imagenet", "datasetVersion": "2025-02-17", "nonRedistributable": false, "display": {"unit": "%", "zeroDay": "2012-01-01", "shortUnit": "%", "yearIsDay": true, "numDecimalPlaces": 1}, "schemaVersion": 2, "processingLevel": "major", "presentation": {"topicTagsLinks": ["Artificial Intelligence"]}, "descriptionKey": ["The top-1 accuracy measure is used to assess how frequently a model's absolute top prediction matches the correct answer from a given set of options.", "Here's an example to illustrate what this benchmark tests: Imagine an image classification model that is presented with an image of an animal. The model assigns probabilities to each potential label and generates its highest-confidence prediction. For instance, when analyzing an image, the model might predict 'Cat' as the most probable label. To evaluate the model's accuracy using the top-1 measure, researchers compare this prediction with the correct label. If the model's top prediction matches the correct label (e.g., if the actual animal in the image is indeed a cat), then the model's prediction is considered correct according to the top-1 accuracy metric. On the other hand, if the model's top prediction does not match the correct label (e.g., if the image shows a dog, but the model predicts a cat), then the model's prediction is considered incorrect based on the top-1 accuracy measure. To calculate the top-1 accuracy, researchers analyze the model's performance on a large dataset where the correct labels are known. They determine the percentage of examples in the dataset where the model's highest-confidence prediction matches the actual label.", "This measure provides a focused evaluation of the model's ability to make accurate predictions by considering only its absolute top guess."], "dimensions": {"years": {"values": [{"id": 0}, {"id": 366}, {"id": 731}, {"id": 1096}, {"id": 1514}, {"id": 1695}, {"id": 2028}, {"id": 2162}, {"id": 2192}, {"id": 2871}, {"id": 2914}, {"id": 2928}, {"id": 2999}, {"id": 3004}, {"id": 3446}, {"id": 3447}, {"id": 3721}, {"id": 3776}]}, "entities": {"values": [{"id": 370003, "name": "Top-1 accuracy", "code": null}]}}, "origins": [{"id": 2882, "title": "AI Performance on Imagenet", "descriptionSnapshot": "ImageNet is one of the most widely used benchmarks for image classification. This dataset includes over 14 million images across 20,000 different object categories such as \u201cstrawberry\u201d or \u201cballoon.\u201d Performance on ImageNet is measured through various accuracy metrics. Top-1 accuracy measures how often a system's single most probable label (out of 1000 possible labels) matches the target label. Top-5 accuracy measures how often any one of the system's five most probable labels (out of 1000 possible labels) matches the target label.\n", "producer": "Papers with Code", "citationFull": "Image Classification on ImageNet. Papers with Code (2025)", "urlMain": "https://paperswithcode.com/sota/image-classification-on-imagenet", "urlDownload": "https://paperswithcode.com/sota/image-classification-on-imagenet", "dateAccessed": "2025-02-17", "datePublished": "2024-07-23", "license": {"url": "https://creativecommons.org/licenses/by-sa/4.0/", "name": "CC BY-SA 4.0"}}]}