{"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/lowformer-hardware-efficient-design-for","title":"LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones","arxiv_id":"2409.03460","date":"2024-09-05","proceeding":null,"authors":["Moritz Nottebaum","Matteo Dunnhofer","Christian Micheloni"],"abstract":"Research in efficient vision backbones is evolving into models that are a mixture of convolutions and transformer blocks. A smart combination of both, architecture-wise and component-wise is mandatory to excel in the speedaccuracy trade-off. Most publications focus on maximizing accuracy and utilize MACs (multiply accumulate operations) as an efficiency metric. The latter however often do not measure accurately how fast a model actually is due to factors like memory access cost and degree of parallelism. We analyzed common modules and architectural design choices for backbones not in terms of MACs, but rather in actual throughput and latency, as the combination of the latter two is a better representation of the efficiency of models in real applications. We applied the conclusions taken from that analysis to create a recipe for increasing hardware-efficiency in macro design. Additionally we introduce a simple slimmed-down version of MultiHead Self-Attention, that aligns with our analysis. We combine both macro and micro design to create a new family of hardware-efficient backbone networks called LowFormer. LowFormer achieves a remarkable speedup in terms of throughput and latency, while achieving similar or better accuracy than current state-of-the-art efficient backbones. In order to prove the generalizability of our hardware-efficient design, we evaluate our method on GPU, mobile GPU and ARM CPU. We further show that the downstream tasks object detection and semantic segmentation profit from our hardware-efficient architecture. Code and models are available at https://github.com/ altair199797/LowFormer.","url_abs":"https://arxiv.org/abs/2409.03460v1","url_pdf":"https://arxiv.org/pdf/2409.03460v1.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":"lowformer-hardware-efficient-design-for","repo_url":"https://github.com/altair199797/lowformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2409.03460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03460"}},"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/altair199797/lowformer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_honours":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":"3f7b732a77ba46cf","entry":"accuracy","repo":"altair199797/lowformer","repo_kind":"official","path":"eval_cls_model.py","file_url":"https://github.com/altair199797/lowformer/blob/HEAD/eval_cls_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3f7b732a77ba46cf"}},{"code_sha256_prefix":"f7db1a3ffb0d1114","entry":"build_kwargs_from_config","repo":"altair199797/lowformer","repo_kind":"official","path":"lowformer_model.py","file_url":"https://github.com/altair199797/lowformer/blob/HEAD/lowformer_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f7db1a3ffb0d1114"}},{"code_sha256_prefix":"f1073b4e93f4484c","entry":"val2list","repo":"altair199797/lowformer","repo_kind":"official","path":"lowformer_model.py","file_url":"https://github.com/altair199797/lowformer/blob/HEAD/lowformer_model.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f1073b4e93f4484c"}},{"code_sha256_prefix":"7a8e24c5db77ad97","entry":"val2tuple","repo":"altair199797/lowformer","repo_kind":"official","path":"lowformer_model.py","file_url":"https://github.com/altair199797/lowformer/blob/HEAD/lowformer_model.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a8e24c5db77ad97"}},{"code_sha256_prefix":"7cb8833e8355fe85","entry":"reset_bn","repo":"altair199797/lowformer","repo_kind":"official","path":"lowformer/models/nn/norm.py","file_url":"https://github.com/altair199797/lowformer/blob/HEAD/lowformer/models/nn/norm.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":"7cb8833e8355fe85"}},{"code_sha256_prefix":"4d5c65845e67bb73","entry":"testrun_it_old","repo":"altair199797/lowformer","repo_kind":"official","path":"eval_cls_model.py","file_url":"https://github.com/altair199797/lowformer/blob/HEAD/eval_cls_model.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":"4d5c65845e67bb73"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}