{"url":"/dataset/sun","name":"SUN","full_name":"SUN Database","description_markdown":"When glancing at a magazine, or browsing the Internet, we are continuously being exposed to photographs. Despite of this overflow of visual information, humans are extremely good at remembering thousands of pictures along with some of their visual details. But not all images are equal in memory. Some stitch to our minds, and other are forgotten. In this paper we focus on the problem of predicting how memorable an image will be. We show that memorability is a stable property of an image that is shared across different viewers. We introduce a database for which we have measured the probability that each picture will be remembered after a single view. We analyze image features and labels that contribute to making an image memorable, and we train a predictor based on global image descriptors. We find that predicting image memorability is a task that can be addressed with current computer vision techniques. Whereas making memorable images is a challenging task in visualization and photography, this work is a first attempt to quantify this useful quality of images.","description_withheld":null,"homepage":"","introduced_date":"2011-08-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/what-makes-an-image-memorable","title":"What makes an image memorable?","first_author":"Isola","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Few-Shot Image Classification","url":"/task/few-shot-image-classification","datasets_with_task":"/datasets/task/few-shot-image-classification"},{"name":"Generalized Few-Shot Learning","url":"/task/generalized-few-shot-learning","datasets_with_task":"/datasets/task/generalized-few-shot-learning"},{"name":"Zero-Shot Transfer Image Classification","url":"/task/zero-shot-transfer-image-classification","datasets_with_task":"/datasets/task/zero-shot-transfer-image-classification"},{"name":"Long-tail learning with class descriptors","url":"/task/long-tail-learning-with-class-descriptors","datasets_with_task":"/datasets/task/long-tail-learning-with-class-descriptors"}],"languages":[],"variants":["SUN","SUN - 0-Shot","SUN-LT"],"data_loaders":[],"num_papers_in_archive":31,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/generalized-few-shot-learning-on-sun","task":"Generalized Few-Shot Learning","dataset_variant":"SUN","rows":5,"metrics":["Per-Class Accuracy (1-shot)","Per-Class Accuracy (2-shots)","Per-Class Accuracy (5-shots)","Per-Class Accuracy (10-shots)"],"first_row_in_archive_order":{"model":"DRAGON","paper":"/paper/long-tail-learning-with-attributes","metrics":{"Per-Class Accuracy (1-shot)":"41.0","Per-Class Accuracy (10-shots)":"48.2","Per-Class Accuracy (2-shots)":"43.8","Per-Class Accuracy (5-shots)":"46.7"},"code_links":[{"title":"dvirsamuel/DRAGON","url":"https://github.com/dvirsamuel/DRAGON"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/long-tail-learning-with-class-descriptors-on-1","task":"Long-tail learning with class descriptors","dataset_variant":"SUN-LT","rows":5,"metrics":["Per-Class Accuracy","Long-Tailed Accuracy"],"first_row_in_archive_order":{"model":"DRAGON + Bal'Loss","paper":"/paper/long-tail-learning-with-attributes","metrics":{"Long-Tailed Accuracy":"38.5","Per-Class Accuracy":"36.1"},"code_links":[{"title":"dvirsamuel/DRAGON","url":"https://github.com/dvirsamuel/DRAGON"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-2","task":"Zero-Shot Transfer Image Classification","dataset_variant":"SUN","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"EVA-CLIP-18B","paper":"/paper/eva-clip-18b-scaling-clip-to-18-billion","metrics":{"Accuracy":"77.7"},"code_links":[{"title":"baaivision/EVA","url":"https://github.com/baaivision/EVA/tree/master/EVA-CLIP-18B"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-image-classification-on-sun-0-shot","task":"Few-Shot Image Classification","dataset_variant":"SUN - 0-Shot","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Synthesised Classifier","paper":"/paper/synthesized-classifiers-for-zero-shot","metrics":{"Accuracy":"62.7%"},"code_links":[{"title":"JudyYe/zero-shot-gcn","url":"https://github.com/JudyYe/zero-shot-gcn"},{"title":"ruotianluo/zsl-gcn-pth","url":"https://github.com/ruotianluo/zsl-gcn-pth"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/eva-clip-18b-scaling-clip-to-18-billion","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","date":"2024-02-06","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","rows_on_this_dataset":1,"code_links":82,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":16,"samples_unverified":4,"pointer_only_for_licence":16,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/long-tail-learning-with-attributes","title":"From Generalized zero-shot learning to long-tail with class descriptors","date":"2020-04-05","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/decoupling-representation-and-classifier-for","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","date":"2019-10-21","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-imbalanced-datasets-with-label","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","date":"2019-06-18","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":2,"samples_unverified":9,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/generalized-zero-and-few-shot-learning-via-1","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","date":"2019-06-01","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/tafe-net-task-aware-feature-embeddings-for-1","title":"TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning","date":"2019-04-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-robust-visual-semantic-embeddings","title":"Learning Robust Visual-Semantic Embeddings","date":"2017-03-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-visual-n-grams-from-web-data","title":"Learning Visual N-Grams from Web Data","date":"2016-12-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/synthesized-classifiers-for-zero-shot","title":"Synthesized Classifiers for Zero-Shot Learning","date":"2016-03-02","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":6,"samples_harvested":45,"samples_ran":22,"samples_unverified":23,"pointer_only_for_licence":23,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}