{"url":"/task/ood-detection","name":"Out of Distribution (OOD) Detection","slug":"ood-detection","description_markdown":"**Out of Distribution (OOD) Detection** is the task of detecting instances that do not belong to the distribution the classifier has been trained on. OOD data is often referred to as \"unseen\" data, as the model has not encountered it during training. \r\n\r\nOOD detection is typically performed by training a model to distinguish between in-distribution (ID) data, which the model has seen during training, and OOD data, which it has not seen. This can be done using a variety of techniques, such as training a separate OOD detector, or modifying the model's architecture or loss function to make it more sensitive to OOD data.","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":629,"papers_with_code":319,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":9,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/out-of-distribution-ood-detection-on-atis","slug":"out-of-distribution-ood-detection-on-atis","dataset":"ATIS","dataset_url":null,"rows_in_archive":1,"metrics":["F1 - macro"],"first_row_in_archive_order":{"model":"BERT + VAE","paper_title":"A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery","paper_url":"/paper/a-hybrid-architecture-for-out-of-domain","paper_date":"2023-03-07","arxiv_id":"2303.04134","code_links":[{"title":"Makbari1997/VAE-KPCA-HDBSCAN","url":"https://github.com/Makbari1997/VAE-KPCA-HDBSCAN"}],"syntology":null}},{"leaderboard":"/sota/out-of-distribution-ood-detection-on-cifar-10","slug":"out-of-distribution-ood-detection-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":1,"metrics":["AUCROC"],"first_row_in_archive_order":{"model":"ZClassifier","paper_title":"ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Space","paper_url":"/paper/zclassifier-temperature-tuning-and-manifold","paper_date":"2025-07-14","arxiv_id":"2507.10638","code_links":[{"title":"ShimSoonYong/ZClassifier","url":"https://github.com/ShimSoonYong/ZClassifier"}],"syntology":null}},{"leaderboard":"/sota/out-of-distribution-ood-detection-on-persian","slug":"out-of-distribution-ood-detection-on-persian","dataset":"Persian-ATIS","dataset_url":"/dataset/persian-atis","rows_in_archive":1,"metrics":["F1 Macro"],"first_row_in_archive_order":{"model":"BERT + VAE","paper_title":"A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery","paper_url":"/paper/a-hybrid-architecture-for-out-of-domain","paper_date":"2023-03-07","arxiv_id":"2303.04134","code_links":[{"title":"Makbari1997/VAE-KPCA-HDBSCAN","url":"https://github.com/Makbari1997/VAE-KPCA-HDBSCAN"}],"syntology":null}},{"leaderboard":"/sota/out-of-distribution-ood-detection-on-snips","slug":"out-of-distribution-ood-detection-on-snips","dataset":"SNIPS","dataset_url":"/dataset/snips","rows_in_archive":1,"metrics":["F1 Macro"],"first_row_in_archive_order":{"model":"BERT + VAE","paper_title":"A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery","paper_url":"/paper/a-hybrid-architecture-for-out-of-domain","paper_date":"2023-03-07","arxiv_id":"2303.04134","code_links":[{"title":"Makbari1997/VAE-KPCA-HDBSCAN","url":"https://github.com/Makbari1997/VAE-KPCA-HDBSCAN"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/snips","name":"SNIPS","full_name":"SNIPS Natural Language Understanding benchmark","num_papers_in_archive":256},{"url":"/dataset/imagenet-o","name":"ImageNet-O","full_name":"","num_papers_in_archive":89},{"url":"/dataset/imagenet-1k-vs-openimage-o","name":"OpenImage-O","full_name":"","num_papers_in_archive":29},{"url":"/dataset/imagenet-1k-vs-ninco","name":"ImageNet-1k vs NINCO","full_name":"No ImageNet Class Objects","num_papers_in_archive":4},{"url":"/dataset/muad","name":"MUAD","full_name":"Multiple Uncertainties for Autonomous Driving","num_papers_in_archive":4},{"url":"/dataset/persian-atis","name":"Persian-ATIS","full_name":"","num_papers_in_archive":2},{"url":"/dataset/fathomnet2023","name":"FathomNet2023","full_name":"FathomNet2023 Competition Dataset","num_papers_in_archive":1},{"url":"/dataset/rmot-223","name":"RMOT-223","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/image-classification","name":"Image Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":319,"tagged_in_all":629,"items":[{"url":"/paper/deep-anomaly-detection-with-outlier-exposure","title":"Deep Anomaly Detection with Outlier Exposure","date":"2018-12-11","arxiv_id":"1812.04606","repositories_listed":9,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/improved-contrastive-divergence-training-of-1","title":"Improved Contrastive Divergence Training of Energy Based Models","date":"2020-12-02","arxiv_id":"2012.01316","repositories_listed":6,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/detecting-out-of-distribution-examples-with","title":"Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices","date":"2019-12-28","arxiv_id":"1912.12510","repositories_listed":5,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/zero-shot-in-distribution-detection-in-multi","title":"GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection","date":"2023-04-10","arxiv_id":"2304.04521","repositories_listed":4,"syntology":{"n":16,"n_ran":5,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/openood-benchmarking-generalized-out-of","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","date":"2022-10-13","arxiv_id":"2210.07242","repositories_listed":4,"syntology":{"n":17,"n_ran":8,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/training-a-helpful-and-harmless-assistant","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","date":"2022-04-12","arxiv_id":"2204.05862","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/generalized-out-of-distribution-detection-a","title":"Generalized Out-of-Distribution Detection: A Survey","date":"2021-10-21","arxiv_id":"2110.11334","repositories_listed":4,"syntology":null},{"url":"/paper/a-simple-fix-to-mahalanobis-distance-for","title":"A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection","date":"2021-06-16","arxiv_id":"2106.09022","repositories_listed":4,"syntology":null},{"url":"/paper/hierarchical-vaes-know-what-they-don-t-know","title":"Hierarchical VAEs Know What They Don't Know","date":"2021-02-16","arxiv_id":"2102.08248","repositories_listed":4,"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":9}},{"url":"/paper/likelihood-ratios-for-out-of-distribution","title":"Likelihood Ratios for Out-of-Distribution Detection","date":"2019-06-07","arxiv_id":"1906.02845","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/openood-v1-5-enhanced-benchmark-for-out-of","title":"OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection","date":"2023-06-15","arxiv_id":"2306.09301","repositories_listed":3,"syntology":null},{"url":"/paper/a-multi-head-model-for-continual-learning-via","title":"A Multi-Head Model for Continual Learning via Out-of-Distribution Replay","date":"2022-08-20","arxiv_id":"2208.09734","repositories_listed":3,"syntology":null},{"url":"/paper/out-of-distribution-detection-via-neural","title":"Out of Distribution Detection via Neural Network Anchoring","date":"2022-07-08","arxiv_id":"2207.04125","repositories_listed":3,"syntology":null},{"url":"/paper/muad-multiple-uncertainties-for-autonomous","title":"MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks","date":"2022-03-02","arxiv_id":"2203.01437","repositories_listed":3,"syntology":null},{"url":"/paper/ssd-a-unified-framework-for-self-supervised-1","title":"SSD: A Unified Framework for Self-Supervised Outlier Detection","date":"2021-03-22","arxiv_id":"2103.12051","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/extremely-simple-multimodal-outlier-synthesis","title":"Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation","date":"2025-05-22","arxiv_id":"2505.16985","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/kernel-pca-for-out-of-distribution-detection-1","title":"Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selections and Approximations","date":"2025-05-21","arxiv_id":"2505.15284","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/a-benchmark-and-evaluation-for-real-world-out","title":"A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models","date":"2025-01-30","arxiv_id":"2501.18463","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/dpu-dynamic-prototype-updating-for-multimodal","title":"DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection","date":"2024-11-12","arxiv_id":"2411.08227","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/lapt-label-driven-automated-prompt-tuning-for","title":"LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models","date":"2024-07-12","arxiv_id":"2407.08966","repositories_listed":2,"syntology":{"n":17,"n_ran":8,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/negative-label-guided-ood-detection-with","title":"Negative Label Guided OOD Detection with Pretrained Vision-Language Models","date":"2024-03-29","arxiv_id":"2403.20078","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/kernel-pca-for-out-of-distribution-detection","title":"Kernel PCA for Out-of-Distribution Detection","date":"2024-02-05","arxiv_id":"2402.02949","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/density-based-feasibility-learning-with","title":"Density-based Feasibility Learning with Normalizing Flows for Introspective Robotic Assembly","date":"2023-07-03","arxiv_id":"2307.01317","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-auroc-co-for-evaluating-out-of","title":"Beyond AUROC & co. for evaluating out-of-distribution detection performance","date":"2023-06-26","arxiv_id":"2306.14658","repositories_listed":2,"syntology":null},{"url":"/paper/locoop-few-shot-out-of-distribution-detection-1","title":"LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning","date":"2023-06-02","arxiv_id":"2306.01293","repositories_listed":2,"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/in-or-out-fixing-imagenet-out-of-distribution","title":"In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation","date":"2023-06-01","arxiv_id":"2306.00826","repositories_listed":2,"syntology":{"n":19,"n_ran":1,"n_unverified":18,"n_pointer_only":0}},{"url":"/paper/fine-tuning-deteriorates-general-textual-out","title":"Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features","date":"2023-01-30","arxiv_id":"2301.12715","repositories_listed":2,"syntology":null},{"url":"/paper/residual-pattern-learning-for-pixel-wise-out","title":"Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation","date":"2022-11-26","arxiv_id":"2211.14512","repositories_listed":2,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/back-to-the-basics-revisiting-out-of","title":"Back to the Basics: Revisiting Out-of-Distribution Detection Baselines","date":"2022-07-07","arxiv_id":"2207.03061","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/poem-out-of-distribution-detection-with","title":"POEM: Out-of-Distribution Detection with Posterior Sampling","date":"2022-06-28","arxiv_id":"2206.13687","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":2}}],"syntology_records":21,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}