{"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/espnet-efficient-spatial-pyramid-of-dilated","title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","arxiv_id":"1803.06815","date":"2018-03-19","proceeding":"ECCV 2018 9","authors":["Sachin Mehta","Mohammad Rastegari","Anat Caspi","Linda Shapiro","Hannaneh Hajishirzi"],"abstract":"We introduce a fast and efficient convolutional neural network, ESPNet, for\nsemantic segmentation of high resolution images under resource constraints.\nESPNet is based on a new convolutional module, efficient spatial pyramid (ESP),\nwhich is efficient in terms of computation, memory, and power. ESPNet is 22\ntimes faster (on a standard GPU) and 180 times smaller than the\nstate-of-the-art semantic segmentation network PSPNet, while its category-wise\naccuracy is only 8% less. We evaluated ESPNet on a variety of semantic\nsegmentation datasets including Cityscapes, PASCAL VOC, and a breast biopsy\nwhole slide image dataset. Under the same constraints on memory and\ncomputation, ESPNet outperforms all the current efficient CNN networks such as\nMobileNet, ShuffleNet, and ENet on both standard metrics and our newly\nintroduced performance metrics that measure efficiency on edge devices. Our\nnetwork can process high resolution images at a rate of 112 and 9 frames per\nsecond on a standard GPU and edge device, respectively.","url_abs":"http://arxiv.org/abs/1803.06815v3","url_pdf":"http://arxiv.org/pdf/1803.06815v3.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":"espnet-efficient-spatial-pyramid-of-dilated","repo_url":"https://github.com/sacmehta/ESPNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"espnet-efficient-spatial-pyramid-of-dilated","repo_url":"https://github.com/klintan/lanenet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"espnet-efficient-spatial-pyramid-of-dilated","repo_url":"https://github.com/klintan/pytorch-lanenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"espnet-efficient-spatial-pyramid-of-dilated","repo_url":"https://github.com/sacmehta/3d-espnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"espnet-efficient-spatial-pyramid-of-dilated","repo_url":"https://github.com/sacmehta/EdgeNets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"espnet-efficient-spatial-pyramid-of-dilated","repo_url":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"espnet-efficient-spatial-pyramid-of-dilated","repo_url":"https://github.com/PaddlePaddle/PaddleSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"espnet-efficient-spatial-pyramid-of-dilated","repo_url":"https://github.com/simuler/ESPNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"real-time-semantic-segmentation","task_name":"Real-Time Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"esp","method_name":"ESP"},{"method_slug":"espnet","method_name":"ESPNet"},{"method_slug":"hierarchical-feature-fusion","method_name":"Hierarchical Feature Fusion"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"prelu","method_name":"PReLU"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"random-scaling","method_name":"Random Scaling"},{"method_slug":"step-decay","method_name":"Step Decay"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"espnet","name":"ESPNet","full_name":"ESPNet"},{"slug":"hierarchical-feature-fusion","name":"Hierarchical Feature Fusion","full_name":"Hierarchical Feature Fusion"}],"results":[{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"ESPNet","rank_in_archive_order":100,"of":105,"metrics":{"Mean IoU (class)":"60.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"ESPNet","rank_in_archive_order":48,"of":51,"metrics":{"Mean IoU":"63.01%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.06815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.06815"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sacmehta/3d-espnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleSeg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sacmehta/ESPNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simuler/ESPNet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sacmehta/EdgeNets","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/klintan/pytorch-lanenet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/klintan/lanenet-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":9,"ran":4,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7b21a1e5f7422c2f","entry":"diceFunction","repo":"sacmehta/3d-espnet","repo_kind":"listed","path":"ComputeDice.py","file_url":"https://github.com/sacmehta/3d-espnet/blob/HEAD/ComputeDice.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b21a1e5f7422c2f"}},{"code_sha256_prefix":"20eb3e6b0aba73e4","entry":"get_test_config","repo":"simuler/ESPNet","repo_kind":"listed","path":"val.py","file_url":"https://github.com/simuler/ESPNet/blob/HEAD/val.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20eb3e6b0aba73e4"}},{"code_sha256_prefix":"8cedd657c11f6f8c","entry":"norm","repo":"sacmehta/3d-espnet","repo_kind":"listed","path":"ComputeDice.py","file_url":"https://github.com/sacmehta/3d-espnet/blob/HEAD/ComputeDice.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8cedd657c11f6f8c"}},{"code_sha256_prefix":"2f75a098ce9f7b0e","entry":"partition_list","repo":"simuler/ESPNet","repo_kind":"listed","path":"paddleseg/core/predict.py","file_url":"https://github.com/simuler/ESPNet/blob/HEAD/paddleseg/core/predict.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f75a098ce9f7b0e"}},{"code_sha256_prefix":"e4705748c848babe","entry":"compute_class_weights","repo":"simuler/ESPNet","repo_kind":"listed","path":"compute_classweight.py","file_url":"https://github.com/simuler/ESPNet/blob/HEAD/compute_classweight.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4705748c848babe"}},{"code_sha256_prefix":"95bccf5957a196e4","entry":"flip_combination","repo":"simuler/ESPNet","repo_kind":"listed","path":"paddleseg/core/infer.py","file_url":"https://github.com/simuler/ESPNet/blob/HEAD/paddleseg/core/infer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"95bccf5957a196e4"}},{"code_sha256_prefix":"a5dbdd4f2d59692e","entry":"get_reverse_list","repo":"simuler/ESPNet","repo_kind":"listed","path":"paddleseg/core/infer.py","file_url":"https://github.com/simuler/ESPNet/blob/HEAD/paddleseg/core/infer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a5dbdd4f2d59692e"}},{"code_sha256_prefix":"0b3ec74bd2e5ed5d","entry":"get_test_config","repo":"simuler/ESPNet","repo_kind":"listed","path":"predict.py","file_url":"https://github.com/simuler/ESPNet/blob/HEAD/predict.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b3ec74bd2e5ed5d"}},{"code_sha256_prefix":"8456f0fd622b9df9","entry":"make_dot","repo":"sacmehta/ESPNet","repo_kind":"official","path":"train/VisualizeGraph.py","file_url":"https://github.com/sacmehta/ESPNet/blob/HEAD/train/VisualizeGraph.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8456f0fd622b9df9"}},{"code_sha256_prefix":"9c1bd7a7658cc12c","entry":"readFile","repo":"simuler/ESPNet","repo_kind":"listed","path":"compute_classweight.py","file_url":"https://github.com/simuler/ESPNet/blob/HEAD/compute_classweight.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9c1bd7a7658cc12c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}