{"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/supervised-compression-for-resource","title":"Supervised Compression for Resource-Constrained Edge Computing Systems","arxiv_id":"2108.11898","date":"2021-08-21","proceeding":null,"authors":["Yoshitomo Matsubara","Ruihan Yang","Marco Levorato","Stephan Mandt"],"abstract":"There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in terms of energy and storage. As a result, the bulk part of the machine learning operation is therefore often carried out on an edge server, where the data is compressed and transmitted. However, compressing data (such as images) leads to transmitting information irrelevant to the supervised task. Another popular approach is to split the deep network between the device and the server while compressing intermediate features. To date, however, such split computing strategies have barely outperformed the aforementioned naive data compression baselines due to their inefficient approaches to feature compression. This paper adopts ideas from knowledge distillation and neural image compression to compress intermediate feature representations more efficiently. Our supervised compression approach uses a teacher model and a student model with a stochastic bottleneck and learnable prior for entropy coding (Entropic Student). We compare our approach to various neural image and feature compression baselines in three vision tasks and found that it achieves better supervised rate-distortion performance while maintaining smaller end-to-end latency. We furthermore show that the learned feature representations can be tuned to serve multiple downstream tasks.","url_abs":"https://arxiv.org/abs/2108.11898v3","url_pdf":"https://arxiv.org/pdf/2108.11898v3.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":"supervised-compression-for-resource","repo_url":"https://github.com/yoshitomo-matsubara/supervised-compression","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"supervised-compression-for-resource","repo_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-compression","task_name":"Data Compression"},{"task_slug":"edge-computing","task_name":"Edge-computing"},{"task_slug":"feature-compression","task_name":"Feature Compression"},{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.11898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11898"}},"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/yoshitomo-matsubara/supervised-compression","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yoshitomo-matsubara/sc2-benchmark","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":16},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1},"listed":{"samples":12,"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":1,"samples":[{"code_sha256_prefix":"a427a6169de8f607","entry":"compute_accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a427a6169de8f607"}},{"code_sha256_prefix":"cd97b267e4c63c03","entry":"check_if_analyzable","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/analysis.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/analysis.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":"cd97b267e4c63c03"}},{"code_sha256_prefix":"032512a773a6431a","entry":"create_faster_rcnn_fpn","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/models/detection/rcnn.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/models/detection/rcnn.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":"032512a773a6431a"}},{"code_sha256_prefix":"2153756735456ef5","entry":"get_analyzer","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/analysis.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/analysis.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":"2153756735456ef5"}},{"code_sha256_prefix":"13699b49bbd77789","entry":"get_compression_model","repo":"yoshitomo-matsubara/supervised-compression","repo_kind":"official","path":"compression/registry.py","file_url":"https://github.com/yoshitomo-matsubara/supervised-compression/blob/HEAD/compression/registry.py","link_basis":"first_harvest_node","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":"13699b49bbd77789"}},{"code_sha256_prefix":"edb9af2bfe3c3d07","entry":"get_detection_model","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/models/detection/registry.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/models/detection/registry.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":"edb9af2bfe3c3d07"}},{"code_sha256_prefix":"5bf69d1c652d53f2","entry":"load_ckpt","repo":"yoshitomo-matsubara/supervised-compression","repo_kind":"official","path":"ckpt_editor.py","file_url":"https://github.com/yoshitomo-matsubara/supervised-compression/blob/HEAD/ckpt_editor.py","link_basis":"first_harvest_node","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":"5bf69d1c652d53f2"}},{"code_sha256_prefix":"fbb9004c52a74063","entry":"register_analysis_class","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/analysis.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/analysis.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":"fbb9004c52a74063"}},{"code_sha256_prefix":"39ed763e55dbf0e9","entry":"register_compressai_model","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/models/registry.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/models/registry.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":"39ed763e55dbf0e9"}},{"code_sha256_prefix":"0d5cd1d5efbacf46","entry":"register_compression_model_class","repo":"yoshitomo-matsubara/supervised-compression","repo_kind":"official","path":"compression/registry.py","file_url":"https://github.com/yoshitomo-matsubara/supervised-compression/blob/HEAD/compression/registry.py","link_basis":"first_harvest_node","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":"0d5cd1d5efbacf46"}},{"code_sha256_prefix":"733180f8f32962be","entry":"register_compression_model_class","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/models/registry.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/models/registry.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":"733180f8f32962be"}},{"code_sha256_prefix":"32164b3ce42adca0","entry":"register_compression_model_func","repo":"yoshitomo-matsubara/supervised-compression","repo_kind":"official","path":"compression/registry.py","file_url":"https://github.com/yoshitomo-matsubara/supervised-compression/blob/HEAD/compression/registry.py","link_basis":"first_harvest_node","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":"32164b3ce42adca0"}},{"code_sha256_prefix":"46791505e5924b54","entry":"register_compression_model_func","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/models/registry.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/models/registry.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":"46791505e5924b54"}},{"code_sha256_prefix":"ead935a341e1f176","entry":"register_layer_class","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/models/layer.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/models/layer.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":"ead935a341e1f176"}},{"code_sha256_prefix":"92d43e7ee8bfedda","entry":"register_layer_func","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/models/layer.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/models/layer.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":"92d43e7ee8bfedda"}},{"code_sha256_prefix":"29dce4ec3c15a305","entry":"register_wrapper_class","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/models/wrapper.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/models/wrapper.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":"29dce4ec3c15a305"}},{"code_sha256_prefix":"09b688d30bb685dc","entry":"wrap_model","repo":"yoshitomo-matsubara/sc2-benchmark","repo_kind":"listed","path":"sc2bench/models/wrapper.py","file_url":"https://github.com/yoshitomo-matsubara/sc2-benchmark/blob/HEAD/sc2bench/models/wrapper.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":"09b688d30bb685dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}