{"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/classification-with-an-edge-improving","title":"Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection","arxiv_id":"1612.01337","date":"2016-12-05","proceeding":null,"authors":["Dimitrios Marmanis","Konrad Schindler","Jan Dirk Wegner","Silvano Galliani","Mihai Datcu","Uwe Stilla"],"abstract":"We present an end-to-end trainable deep convolutional neural network (DCNN)\nfor semantic segmentation with built-in awareness of semantically meaningful\nboundaries. Semantic segmentation is a fundamental remote sensing task, and\nmost state-of-the-art methods rely on DCNNs as their workhorse. A major reason\nfor their success is that deep networks learn to accumulate contextual\ninformation over very large windows (receptive fields). However, this success\ncomes at a cost, since the associated loss of effecive spatial resolution\nwashes out high-frequency details and leads to blurry object boundaries. Here,\nwe propose to counter this effect by combining semantic segmentation with\nsemantically informed edge detection, thus making class-boundaries explicit in\nthe model, First, we construct a comparatively simple, memory-efficient model\nby adding boundary detection to the Segnet encoder-decoder architecture.\nSecond, we also include boundary detection in FCN-type models and set up a\nhigh-end classifier ensemble. We show that boundary detection significantly\nimproves semantic segmentation with CNNs. Our high-end ensemble achieves > 90%\noverall accuracy on the ISPRS Vaihingen benchmark.","url_abs":"http://arxiv.org/abs/1612.01337v2","url_pdf":"http://arxiv.org/pdf/1612.01337v2.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":"classification-with-an-edge-improving","repo_url":"https://github.com/deep-unlearn/ISPRS-Classification-With-an-Edge","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"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":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1612.01337","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}