{"url":"/dataset/caltech-101","name":"Caltech-101","full_name":null,"description_markdown":"The Caltech101 dataset contains images from 101 object categories (e.g., “helicopter”, “elephant” and “chair” etc.) and a background category that contains the images not from the 101 object categories. For each object category, there are about 40 to 800 images, while most classes have about 50 images. The resolution of the image is roughly about 300×200 pixels.\r\n\r\nSource: [Simple and Efficient Learning using Privileged Information](https://arxiv.org/abs/1604.01518)","description_withheld":null,"homepage":"http://www.vision.caltech.edu/Image_Datasets/Caltech101/","introduced_date":"2004-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories","first_author":null,"url":"https://doi.org/10.1109/CVPR.2004.383"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Zero-Shot Learning","url":"/task/zero-shot-learning","datasets_with_task":"/datasets/task/zero-shot-learning"},{"name":"Semi-Supervised Image Classification","url":"/task/semi-supervised-image-classification","datasets_with_task":"/datasets/task/semi-supervised-image-classification"},{"name":"Image Clustering","url":"/task/image-clustering","datasets_with_task":"/datasets/task/image-clustering"},{"name":"Fine-Grained Image Classification","url":"/task/fine-grained-image-classification","datasets_with_task":"/datasets/task/fine-grained-image-classification"},{"name":"Unsupervised Anomaly Detection","url":"/task/unsupervised-anomaly-detection","datasets_with_task":"/datasets/task/unsupervised-anomaly-detection"},{"name":"Transductive Zero-Shot Classification","url":"/task/transductive-zero-shot-classification","datasets_with_task":"/datasets/task/transductive-zero-shot-classification"},{"name":"Prompt Engineering","url":"/task/prompt-engineering","datasets_with_task":"/datasets/task/prompt-engineering"},{"name":"Density Estimation","url":"/task/density-estimation","datasets_with_task":"/datasets/task/density-estimation"},{"name":"Semantic correspondence","url":"/task/semantic-correspondence","datasets_with_task":"/datasets/task/semantic-correspondence"}],"languages":[],"variants":["Caltech-101","Caltech-101, 202 Labels"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.Caltech101.html","frameworks":["pytorch"]},{"repo":"https://github.com/voxel51/fiftyone","url":"https://docs.voxel51.com/user_guide/dataset_zoo/datasets.html#caltech-101","frameworks":["tf","pytorch"]},{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/caltech-101-dataset","frameworks":["tf","pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/caltech101","frameworks":["tf","jax"]}],"num_papers_in_archive":709,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/fine-grained-image-classification-on-caltech","task":"Fine-Grained Image Classification","dataset_variant":"Caltech-101","rows":18,"metrics":["Top-1 Error Rate","Accuracy"],"first_row_in_archive_order":{"model":"VIT-L/16","paper":"/paper/reduction-of-class-activation-uncertainty","metrics":{"Top-1 Error Rate":"1.98%"},"code_links":[{"title":"dipuk0506/SpinalNet","url":"https://github.com/dipuk0506/SpinalNet"},{"title":"dipuk0506/uq","url":"https://github.com/dipuk0506/uq"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/prompt-engineering-on-caltech-101","task":"Prompt Engineering","dataset_variant":"Caltech-101","rows":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper":"/paper/promptkd-unsupervised-prompt-distillation-for","metrics":{"Harmonic mean":"97.77"},"code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/density-estimation-on-caltech-101","task":"Density Estimation","dataset_variant":"Caltech-101","rows":3,"metrics":["Negative ELBO","NLL","MMD-L2","COV-L2"],"first_row_in_archive_order":{"model":"B-NAF","paper":"/paper/block-neural-autoregressive-flow","metrics":{"NLL":"105.42","Negative ELBO":"94.91"},"code_links":[{"title":"nicola-decao/BNAF","url":"https://github.com/nicola-decao/BNAF"},{"title":"metachenyiyan/BreezeForest","url":"https://github.com/metachenyiyan/BreezeForest"},{"title":"Naagar/Glow_NormalizingFlow_implimentation","url":"https://github.com/Naagar/Glow_NormalizingFlow_implimentation"},{"title":"sshish/NF","url":"https://github.com/sshish/NF"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-correspondence-on-caltech-101","task":"Semantic correspondence","dataset_variant":"Caltech-101","rows":2,"metrics":["IoU","LT-ACC","IoU (weak)","LT-ACC (weak)"],"first_row_in_archive_order":{"model":"HPF","paper":"/paper/hyperpixel-flow-semantic-correspondence-with","metrics":{"IoU":"63","LT-ACC":"87"},"code_links":[{"title":"juhongm999/hpf","url":"https://github.com/juhongm999/hpf"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-learning-on-caltech-101","task":"Zero-Shot Learning","dataset_variant":"Caltech-101","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ZLaP","paper":"/paper/label-propagation-for-zero-shot","metrics":{"Accuracy":"84"},"code_links":[{"title":"vladan-stojnic/zlap","url":"https://github.com/vladan-stojnic/zlap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-clustering-on-caltech-101","task":"Image Clustering","dataset_variant":"Caltech-101","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TURTLE (CLIP + DINOv2)","paper":"/paper/let-go-of-your-labels-with-unsupervised-1","metrics":{"Accuracy":"89.8"},"code_links":[{"title":"mlbio-epfl/turtle","url":"https://github.com/mlbio-epfl/turtle"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-image-classification-on-8","task":"Semi-Supervised Image Classification","dataset_variant":"Caltech-101","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"UL-Hopfield (ULH)","paper":"/paper/unsupervised-learning-using-pretrained-cnn","metrics":{"Accuracy":"91.00%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-image-classification-on-9","task":"Semi-Supervised Image Classification","dataset_variant":"Caltech-101, 202 Labels","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"UL-Hopfield (ULH)","paper":"/paper/unsupervised-learning-using-pretrained-cnn","metrics":{"Accuracy":"91.00%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/transductive-zero-shot-classification-on-6","task":"Transductive Zero-Shot Classification","dataset_variant":"Caltech-101","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ZLaP","paper":"/paper/label-propagation-for-zero-shot","metrics":{"Accuracy":"83.7"},"code_links":[{"title":"vladan-stojnic/zlap","url":"https://github.com/vladan-stojnic/zlap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-caltech-101-1","task":"Unsupervised Anomaly Detection","dataset_variant":"Caltech-101","rows":1,"metrics":["AUC (outlier ratio = 0.5)"],"first_row_in_archive_order":{"model":"RSRAE","paper":"/paper/robust-subspace-recovery-layer-for","metrics":{"AUC (outlier ratio = 0.5)":"0.772"},"code_links":[{"title":"dmzou/RSRAE","url":"https://github.com/dmzou/RSRAE"},{"title":"marrrcin/rsrlayer-pytorch","url":"https://github.com/marrrcin/rsrlayer-pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mmrl-parameter-efficient-and-interaction","title":"MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models","date":"2025-05-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mmrl-multi-modal-representation-learning-for","title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models","date":"2025-03-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stochastic-subsampling-with-average-pooling","title":"Stochastic Subsampling With Average Pooling","date":"2024-09-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hpt-hierarchically-prompting-vision-language","title":"HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling","date":"2024-08-27","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/let-go-of-your-labels-with-unsupervised-1","title":"Let Go of Your Labels with Unsupervised Transfer","date":"2024-06-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/label-propagation-for-zero-shot","title":"Label Propagation for Zero-shot Classification with Vision-Language Models","date":"2024-04-05","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/prompt-learning-via-meta-regularization","title":"Prompt Learning via Meta-Regularization","date":"2024-04-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":4,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/paddingflow-improving-normalizing-flows-with","title":"PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise","date":"2024-03-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/promptkd-unsupervised-prompt-distillation-for","title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","date":"2024-03-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","date":"2023-12-11","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dept-decoupled-prompt-tuning","title":"DePT: Decoupled Prompt Tuning","date":"2023-09-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":4,"samples_unverified":4,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/read-only-prompt-optimization-for-vision","title":"Read-only Prompt Optimization for Vision-Language Few-shot Learning","date":"2023-08-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-regulating-prompts-foundational-model","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","date":"2023-07-13","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":7,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/consistency-guided-prompt-learning-for-vision","title":"Consistency-guided Prompt Learning for Vision-Language Models","date":"2023-06-01","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/understanding-gaussian-attention-bias-of","title":"Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields","date":"2023-05-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/reduction-of-class-activation-uncertainty","title":"Reduction of Class Activation Uncertainty with Background Information","date":"2023-05-05","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/how-to-use-dropout-correctly-on-residual","title":"How to Use Dropout Correctly on Residual Networks with Batch Normalization","date":"2023-02-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/on-the-ideal-number-of-groups-for-isometric","title":"On the Ideal Number of Groups for Isometric Gradient Propagation","date":"2023-02-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-domain-invariant-prompt-for-vision","title":"Learning Domain Invariant Prompt for Vision-Language Models","date":"2022-12-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/maple-multi-modal-prompt-learning","title":"MaPLe: Multi-modal Prompt Learning","date":"2022-10-06","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-continual-development-methodology-for-large","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","date":"2022-09-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/an-evolutionary-approach-to-dynamic","title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","date":"2022-05-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bamboo-building-mega-scale-vision-dataset","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","date":"2022-03-15","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/conditional-prompt-learning-for-vision","title":"Conditional Prompt Learning for Vision-Language Models","date":"2022-03-10","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vision-models-are-more-robust-and-fair-when","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","date":"2022-02-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-learning-by-estimating-twin-1","title":"Self-Supervised Learning by Estimating Twin Class Distributions","date":"2021-10-14","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":5,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dead-pixel-test-using-effective-receptive","title":"Dead Pixel Test Using Effective Receptive Field","date":"2021-08-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/with-a-little-help-from-my-friends-nearest","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","date":"2021-04-29","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/progressivespinalnet-architecture-for-fc","title":"ProgressiveSpinalNet architecture for FC layers","date":"2021-03-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/learning-to-compose-hypercolumns-for-visual","title":"Learning to Compose Hypercolumns for Visual Correspondence","date":"2020-07-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/spinalnet-deep-neural-network-with-gradual-1","title":"SpinalNet: Deep Neural Network with Gradual Input","date":"2020-07-07","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/hyperpixel-flow-semantic-correspondence-with","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","date":"2019-08-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/block-neural-autoregressive-flow","title":"Block Neural Autoregressive Flow","date":"2019-04-09","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/robust-subspace-recovery-layer-for","title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","date":"2019-03-30","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/ffjord-free-form-continuous-dynamics-for","title":"FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models","date":"2018-10-02","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/autoaugment-learning-augmentation-policies","title":"AutoAugment: Learning Augmentation Policies from Data","date":"2018-05-24","rows_on_this_dataset":1,"code_links":33,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":43,"samples_ran":6,"samples_unverified":37,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-learning-using-pretrained-cnn","title":"Unsupervised Learning using Pretrained CNN and Associative Memory Bank","date":"2018-05-02","rows_on_this_dataset":3,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":20,"samples_harvested":189,"samples_ran":77,"samples_unverified":112,"pointer_only_for_licence":33,"papers_with_no_sample_that_ran":3,"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."}