{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/traffic-sign-classification-using-deep","title":"Traffic Sign Classification Using Deep Inception Based Convolutional Networks","arxiv_id":"1511.02992","date":"2015-11-10","proceeding":null,"authors":["Mrinal Haloi"],"abstract":"In this work, we propose a novel deep network for traffic sign classification\nthat achieves outstanding performance on GTSRB surpassing all previous methods.\nOur deep network consists of spatial transformer layers and a modified version\nof inception module specifically designed for capturing local and global\nfeatures together. This features adoption allows our network to classify\nprecisely intraclass samples even under deformations. Use of spatial\ntransformer layer makes this network more robust to deformations such as\ntranslation, rotation, scaling of input images. Unlike existing approaches that\nare developed with hand-crafted features, multiple deep networks with huge\nparameters and data augmentations, our method addresses the concern of\nexploding parameters and augmentations. We have achieved the state-of-the-art\nperformance of 99.81\\% on GTSRB dataset.","url_abs":"http://arxiv.org/abs/1511.02992v2","url_pdf":"http://arxiv.org/pdf/1511.02992v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"traffic-sign-classification-using-deep","repo_url":"https://github.com/shivendrashahi/Final_Project_Traffic_Sign","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"traffic-sign-classification-using-deep","repo_url":"https://github.com/vxy10/p2-TrafficSigns","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"traffic-sign-recognition","task_name":"Traffic Sign Recognition"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"inception-module","method_name":"Inception Module"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"spatial-transformer","method_name":"Spatial Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.02992","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}