{"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/squeeze-segnet-a-new-fast-deep-convolutional","title":"Squeeze-SegNet: A new fast Deep Convolutional Neural Network for Semantic Segmentation","arxiv_id":"1711.05491","date":"2017-11-15","proceeding":null,"authors":["Geraldin Nanfack","Azeddine Elhassouny","Rachid Oulad Haj Thami"],"abstract":"The recent researches in Deep Convolutional Neural Network have focused their\nattention on improving accuracy that provide significant advances. However, if\nthey were limited to classification tasks, nowadays with contributions from\nScientific Communities who are embarking in this field, they have become very\nuseful in higher level tasks such as object detection and pixel-wise semantic\nsegmentation. Thus, brilliant ideas in the field of semantic segmentation with\ndeep learning have completed the state of the art of accuracy, however this\narchitectures become very difficult to apply in embedded systems as is the case\nfor autonomous driving. We present a new Deep fully Convolutional Neural\nNetwork for pixel-wise semantic segmentation which we call Squeeze-SegNet. The\narchitecture is based on Encoder-Decoder style. We use a SqueezeNet-like\nencoder and a decoder formed by our proposed squeeze-decoder module and\nupsample layer using downsample indices like in SegNet and we add a\ndeconvolution layer to provide final multi-channel feature map. On datasets\nlike Camvid or City-states, our net gets SegNet-level accuracy with less than\n10 times fewer parameters than SegNet.","url_abs":"http://arxiv.org/abs/1711.05491v1","url_pdf":"http://arxiv.org/pdf/1711.05491v1.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":"squeeze-segnet-a-new-fast-deep-convolutional","repo_url":"https://github.com/ajoshi944/Segmentation-severstal-steel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"segnet","method_name":"SegNet"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}