{"url":"/task/traffic-sign-recognition","name":"Traffic Sign Recognition","slug":"traffic-sign-recognition","description_markdown":"Traffic sign recognition is the task of recognising traffic signs in an image or video.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Novel Deep Learning Model for Traffic Sign Detection Using Capsule\r\nNetworks ](https://arxiv.org/pdf/1805.04424v1.pdf) )</span>","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":127,"papers_with_code":43,"benchmarks":10,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"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":7,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/traffic-sign-recognition-on-tsinghua-tencent","slug":"traffic-sign-recognition-on-tsinghua-tencent","dataset":"Tsinghua-Tencent 100K","dataset_url":"/dataset/tsinghua-tencent-100k","rows_in_archive":6,"metrics":["MAP","FPS (V100, b=1)","Accuracy"],"first_row_in_archive_order":{"model":"TSR-SA(with RFB-C)","paper_title":"A real-time and high-precision method for small traffic-signs recognition","paper_url":"/paper/a-real-time-and-high-precision-method-for","paper_date":"2021-09-25","arxiv_id":null,"code_links":[{"title":"Kunkun-Jia/TSR-SA","url":"https://github.com/Kunkun-Jia/TSR-SA"}],"syntology":null}},{"leaderboard":"/sota/traffic-sign-recognition-on-dfg-traffic-sign-1","slug":"traffic-sign-recognition-on-dfg-traffic-sign-1","dataset":"DFG traffic-sign dataset","dataset_url":null,"rows_in_archive":5,"metrics":["mAP@0.50","mAP @0.5:0.95"],"first_row_in_archive_order":{"model":"Mask R-CNN with adaptations for traffic sings and augmentations (ResNet50)","paper_title":"Deep Learning for Large-Scale Traffic-Sign Detection and Recognition","paper_url":"/paper/deep-learning-for-large-scale-traffic-sign","paper_date":"2019-04-01","arxiv_id":"1904.00649","code_links":[{"title":"skokec/detectron-traffic-signs","url":"https://github.com/skokec/detectron-traffic-signs"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/traffic-sign-recognition-on-gtsrb","slug":"traffic-sign-recognition-on-gtsrb","dataset":"GTSRB","dataset_url":"/dataset/gtsrb","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CNN with 3 Spatial Transformers","paper_title":"Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods","paper_url":"/paper/deep-neural-network-for-traffic-sign","paper_date":"2018-03-01","arxiv_id":null,"code_links":[{"title":"aarcosg/tsr-torch","url":"https://github.com/aarcosg/tsr-torch"}],"syntology":null}},{"leaderboard":"/sota/traffic-sign-recognition-on-bosch-small","slug":"traffic-sign-recognition-on-bosch-small","dataset":"Bosch Small Traffic Lights","dataset_url":null,"rows_in_archive":3,"metrics":["MAP"],"first_row_in_archive_order":{"model":"Hierarchical + Background Threshold Model","paper_title":"A Hierarchical Deep Architecture and Mini-Batch Selection Method For Joint Traffic Sign and Light Detection","paper_url":"/paper/a-hierarchical-deep-architecture-and-mini","paper_date":"2018-06-20","arxiv_id":"1806.07987","code_links":[{"title":"bosch-ros-pkg/bstld","url":"https://github.com/bosch-ros-pkg/bstld"},{"title":"sovit-123/traffic-light-detection-using-yolov3","url":"https://github.com/sovit-123/traffic-light-detection-using-yolov3"}],"syntology":null}},{"leaderboard":"/sota/traffic-sign-recognition-on-swedish-traffic-2","slug":"traffic-sign-recognition-on-swedish-traffic-2","dataset":"Swedish traffic-sign dataset (STSD)","dataset_url":null,"rows_in_archive":2,"metrics":["mAP@0.50"],"first_row_in_archive_order":{"model":"Mask R-CNN with adaptations for traffic sings (ResNet50)","paper_title":"Deep Learning for Large-Scale Traffic-Sign Detection and Recognition","paper_url":"/paper/deep-learning-for-large-scale-traffic-sign","paper_date":"2019-04-01","arxiv_id":"1904.00649","code_links":[{"title":"skokec/detectron-traffic-signs","url":"https://github.com/skokec/detectron-traffic-signs"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/traffic-sign-recognition-on-belgalogos","slug":"traffic-sign-recognition-on-belgalogos","dataset":"BelgaLogos","dataset_url":"/dataset/belgalogos","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Sill-Net","paper_title":"Sill-Net: Feature Augmentation with Separated Illumination Representation","paper_url":"/paper/sill-net-feature-augmentation-with-separated","paper_date":"2021-02-06","arxiv_id":"2102.03539","code_links":[{"title":"lanfenghuanyu/Sill-Net","url":"https://github.com/lanfenghuanyu/Sill-Net"}],"syntology":null}},{"leaderboard":"/sota/traffic-sign-recognition-on-belgian-traffic","slug":"traffic-sign-recognition-on-belgian-traffic","dataset":"Belgian Traffic Sign Classification","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Sill-Net","paper_title":"Sill-Net: Feature Augmentation with Separated Illumination Representation","paper_url":"/paper/sill-net-feature-augmentation-with-separated","paper_date":"2021-02-06","arxiv_id":"2102.03539","code_links":[{"title":"lanfenghuanyu/Sill-Net","url":"https://github.com/lanfenghuanyu/Sill-Net"}],"syntology":null}},{"leaderboard":"/sota/traffic-sign-recognition-on-chinese-traffic","slug":"traffic-sign-recognition-on-chinese-traffic","dataset":"Chinese Traffic Sign Database","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Sill-Net","paper_title":"Sill-Net: Feature Augmentation with Separated Illumination Representation","paper_url":"/paper/sill-net-feature-augmentation-with-separated","paper_date":"2021-02-06","arxiv_id":"2102.03539","code_links":[{"title":"lanfenghuanyu/Sill-Net","url":"https://github.com/lanfenghuanyu/Sill-Net"}],"syntology":null}},{"leaderboard":"/sota/traffic-sign-recognition-on-flickrlogos-32","slug":"traffic-sign-recognition-on-flickrlogos-32","dataset":"FlickrLogos-32","dataset_url":"/dataset/flickrlogos-32","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Sill-Net","paper_title":"Sill-Net: Feature Augmentation with Separated Illumination Representation","paper_url":"/paper/sill-net-feature-augmentation-with-separated","paper_date":"2021-02-06","arxiv_id":"2102.03539","code_links":[{"title":"lanfenghuanyu/Sill-Net","url":"https://github.com/lanfenghuanyu/Sill-Net"}],"syntology":null}},{"leaderboard":"/sota/traffic-sign-recognition-on-toplogo-10","slug":"traffic-sign-recognition-on-toplogo-10","dataset":"TopLogo-10","dataset_url":"/dataset/toplogo-10","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Sill-Net","paper_title":"Sill-Net: Feature Augmentation with Separated Illumination Representation","paper_url":"/paper/sill-net-feature-augmentation-with-separated","paper_date":"2021-02-06","arxiv_id":"2102.03539","code_links":[{"title":"lanfenghuanyu/Sill-Net","url":"https://github.com/lanfenghuanyu/Sill-Net"}],"syntology":null}}],"datasets":[{"url":"/dataset/gtsrb","name":"GTSRB","full_name":"German Traffic Sign Recognition Benchmark","num_papers_in_archive":374},{"url":"/dataset/flickrlogos-32","name":"FlickrLogos-32","full_name":"","num_papers_in_archive":26},{"url":"/dataset/cure-tsr","name":"CURE-TSR","full_name":"CURE Traffic Sign Recognition","num_papers_in_archive":16},{"url":"/dataset/toplogo-10","name":"TopLogo-10","full_name":"","num_papers_in_archive":6},{"url":"/dataset/cure-tsd","name":"CURE-TSD","full_name":"CURE Traffic Sign Detection","num_papers_in_archive":3},{"url":"/dataset/tsinghua-tencent-100k","name":"Tsinghua-Tencent 100K","full_name":"Traffic-Sign Detection and Classification in the Wild","num_papers_in_archive":3},{"url":"/dataset/belgalogos","name":"BelgaLogos","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/autonomous-vehicles","name":"Autonomous Vehicles"}],"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":43,"tagged_in_all":127,"items":[{"url":"/paper/architecturing-binarized-neural-networks-for","title":"Architecturing Binarized Neural Networks for Traffic Sign Recognition","date":"2023-03-27","arxiv_id":"2303.15005","repositories_listed":4,"syntology":null},{"url":"/paper/novel-deep-learning-model-for-traffic-sign","title":"Novel Deep Learning Model for Traffic Sign Detection Using Capsule Networks","date":"2018-05-11","arxiv_id":"1805.04424","repositories_listed":3,"syntology":null},{"url":"/paper/targeted-attention-attack-on-deep-learning","title":"Targeted Physical-World Attention Attack on Deep Learning Models in Road Sign Recognition","date":"2020-10-09","arxiv_id":"2010.04331","repositories_listed":2,"syntology":null},{"url":"/paper/traffic-sign-detection-under-challenging","title":"Traffic Sign Detection under Challenging Conditions: A Deeper Look Into Performance Variations and Spectral Characteristics","date":"2019-08-29","arxiv_id":"1908.11262","repositories_listed":2,"syntology":null},{"url":"/paper/a-hierarchical-deep-architecture-and-mini","title":"A Hierarchical Deep Architecture and Mini-Batch Selection Method For Joint Traffic Sign and Light Detection","date":"2018-06-20","arxiv_id":"1806.07987","repositories_listed":2,"syntology":null},{"url":"/paper/traffic-sign-classification-using-deep","title":"Traffic Sign Classification Using Deep Inception Based Convolutional Networks","date":"2015-11-10","arxiv_id":"1511.02992","repositories_listed":2,"syntology":null},{"url":"/paper/evaluating-adversarial-attacks-on-traffic","title":"Evaluating Adversarial Attacks on Traffic Sign Classifiers beyond Standard Baselines","date":"2024-12-12","arxiv_id":"2412.09150","repositories_listed":1,"syntology":null},{"url":"/paper/causaldiff-causality-inspired-disentanglement","title":"CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense","date":"2024-10-30","arxiv_id":"2410.23091","repositories_listed":1,"syntology":{"n":17,"n_ran":3,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/tsclip-robust-clip-fine-tuning-for-worldwide","title":"TSCLIP: Robust CLIP Fine-Tuning for Worldwide Cross-Regional Traffic Sign Recognition","date":"2024-09-23","arxiv_id":"2409.15077","repositories_listed":1,"syntology":null},{"url":"/paper/seqnet-sequential-networks-for-one-shot","title":"SeqNet: Sequential Networks for One-Shot Traffic Sign Recognition With Transfer Learning","date":"2024-09-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/horizontal-class-backdoor-to-deep-learning","title":"Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense","date":"2023-10-01","arxiv_id":"2310.00542","repositories_listed":1,"syntology":{"n":22,"n_ran":15,"n_unverified":7,"n_pointer_only":7}},{"url":"/paper/benchmarking-local-robustness-of-high","title":"Benchmarking Local Robustness of High-Accuracy Binary Neural Networks for Enhanced Traffic Sign Recognition","date":"2023-09-25","arxiv_id":"2310.03033","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-certification-for","title":"Adversarial Robustness Certification for Bayesian Neural Networks","date":"2023-06-23","arxiv_id":"2306.13614","repositories_listed":1,"syntology":null},{"url":"/paper/zenseact-open-dataset-a-large-scale-and","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","date":"2023-05-03","arxiv_id":"2305.02008","repositories_listed":1,"syntology":null},{"url":"/paper/traffic-sign-recognition-dataset-and-data","title":"Traffic Sign Recognition Dataset and Data Augmentation","date":"2023-03-31","arxiv_id":"2303.18037","repositories_listed":1,"syntology":null},{"url":"/paper/robust-transformer-with-locality-inductive","title":"Robust Transformer with Locality Inductive Bias and Feature Normalization","date":"2023-01-27","arxiv_id":"2301.11553","repositories_listed":1,"syntology":null},{"url":"/paper/simultaneously-optimizing-perturbations-and","title":"Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks","date":"2022-12-26","arxiv_id":"2212.12995","repositories_listed":1,"syntology":null},{"url":"/paper/glare-a-dataset-for-traffic-sign-detection-in","title":"GLARE: A Dataset for Traffic Sign Detection in Sun Glare","date":"2022-09-19","arxiv_id":"2209.08716","repositories_listed":1,"syntology":null},{"url":"/paper/keep-your-distance-determining-sampling-and","title":"Keep your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring","date":"2022-07-11","arxiv_id":"2207.05078","repositories_listed":1,"syntology":null},{"url":"/paper/shadows-can-be-dangerous-stealthy-and","title":"Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon","date":"2022-03-08","arxiv_id":"2203.03818","repositories_listed":1,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/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","arxiv_id":"2202.08360","repositories_listed":1,"syntology":null},{"url":"/paper/improving-traffic-sign-recognition-by-active","title":"Improving traffic sign recognition by active search","date":"2021-11-29","arxiv_id":"2111.14426","repositories_listed":1,"syntology":null},{"url":"/paper/a-real-time-and-high-precision-method-for","title":"A real-time and high-precision method for small traffic-signs recognition","date":"2021-09-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/toward-improving-confidence-in-autonomous","title":"Toward Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition Systems","date":"2021-08-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/meaningful-adversarial-stickers-for-face","title":"Adversarial Sticker: A Stealthy Attack Method in the Physical World","date":"2021-04-14","arxiv_id":"2104.06728","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/sill-net-feature-augmentation-with-separated","title":"Sill-Net: Feature Augmentation with Separated Illumination Representation","date":"2021-02-06","arxiv_id":"2102.03539","repositories_listed":1,"syntology":null},{"url":"/paper/slap-improving-physical-adversarial-examples","title":"SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbations","date":"2020-07-08","arxiv_id":"2007.04137","repositories_listed":1,"syntology":null},{"url":"/paper/discriminative-feature-alignment","title":"Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment","date":"2020-06-23","arxiv_id":"2006.12770","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/learning-from-context-agnostic-synthetic-data","title":"Towards Context-Agnostic Learning Using Synthetic Data","date":"2020-05-29","arxiv_id":"2005.14707","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/nettailor-tuning-the-architecture-not-just-1","title":"NetTailor: Tuning the Architecture, Not Just the Weights","date":"2019-06-29","arxiv_id":"1907.00274","repositories_listed":1,"syntology":null}],"syntology_records":6,"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"}}