{"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/squeezenas-fast-neural-architecture-search","title":"SqueezeNAS: Fast neural architecture search for faster semantic segmentation","arxiv_id":"1908.01748","date":"2019-08-05","proceeding":null,"authors":["Albert Shaw","Daniel Hunter","Forrest Iandola","Sammy Sidhu"],"abstract":"For real time applications utilizing Deep Neural Networks (DNNs), it is critical that the models achieve high-accuracy on the target task and low-latency inference on the target computing platform. While Neural Architecture Search (NAS) has been effectively used to develop low-latency networks for image classification, there has been relatively little effort to use NAS to optimize DNN architectures for other vision tasks. In this work, we present what we believe to be the first proxyless hardware-aware search targeted for dense semantic segmentation. With this approach, we advance the state-of-the-art accuracy for latency-optimized networks on the Cityscapes semantic segmentation dataset. Our latency-optimized small SqueezeNAS network achieves 68.02% validation class mIOU with less than 35 ms inference times on the NVIDIA AGX Xavier. Our latency-optimized large SqueezeNAS network achieves 73.62% class mIOU with less than 100 ms inference times. We demonstrate that significant performance gains are possible by utilizing NAS to find networks optimized for both the specific task and inference hardware. We also present detailed analysis comparing our networks to recent state-of-the-art architectures.","url_abs":"https://arxiv.org/abs/1908.01748v2","url_pdf":"https://arxiv.org/pdf/1908.01748v2.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":"squeezenas-fast-neural-architecture-search","repo_url":"https://github.com/ashaw596/squeezenas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"SqueezeNAS (LAT Large)","rank_in_archive_order":69,"of":105,"metrics":{"Mean IoU (class)":"72.5%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"SqueezeNAS (LAT Small)","rank_in_archive_order":92,"of":105,"metrics":{"Mean IoU (class)":"66.8%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"SqueezeNAS (LAT XLarge)","rank_in_archive_order":73,"of":99,"metrics":{"mIoU":"75.2%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"SqueezeNAS (LAT Large)","rank_in_archive_order":79,"of":99,"metrics":{"mIoU":"73.6%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"SqueezeNAS (LAT Small)","rank_in_archive_order":91,"of":99,"metrics":{"mIoU":"68.0%"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.01748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.01748"}},"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/ashaw596/squeezenas","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"repositories":1}},"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":"d893babcda9f9805","entry":"conv3x3_bn","repo":"ashaw596/squeezenas","repo_kind":"listed","path":"arch/utils.py","file_url":"https://github.com/ashaw596/squeezenas/blob/HEAD/arch/utils.py","link_basis":"harvester_set","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":"d893babcda9f9805"}},{"code_sha256_prefix":"2e73e8e10fb7ce2e","entry":"conv_1x1_bn","repo":"ashaw596/squeezenas","repo_kind":"listed","path":"arch/utils.py","file_url":"https://github.com/ashaw596/squeezenas/blob/HEAD/arch/utils.py","link_basis":"harvester_set","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":"2e73e8e10fb7ce2e"}},{"code_sha256_prefix":"f1cb428620e0494e","entry":"get_named_arch_params","repo":"ashaw596/squeezenas","repo_kind":"listed","path":"search/arch_search.py","file_url":"https://github.com/ashaw596/squeezenas/blob/HEAD/search/arch_search.py","link_basis":"harvester_set","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":"f1cb428620e0494e"}},{"code_sha256_prefix":"7cdc524e995bcb40","entry":"get_named_model_params","repo":"ashaw596/squeezenas","repo_kind":"listed","path":"search/arch_search.py","file_url":"https://github.com/ashaw596/squeezenas/blob/HEAD/search/arch_search.py","link_basis":"harvester_set","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":"7cdc524e995bcb40"}},{"code_sha256_prefix":"006e84a4cd167e2d","entry":"gumbel_softmax_sample","repo":"ashaw596/squeezenas","repo_kind":"listed","path":"search/arch_search.py","file_url":"https://github.com/ashaw596/squeezenas/blob/HEAD/search/arch_search.py","link_basis":"harvester_set","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":"006e84a4cd167e2d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}