{"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/optimal-ann-snn-conversion-for-high-accuracy-1","title":"Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks","arxiv_id":"2303.04347","date":"2023-03-08","proceeding":"ICLR 2022 4","authors":["Tong Bu","Wei Fang","Jianhao Ding","Penglin Dai","Zhaofei Yu","Tiejun Huang"],"abstract":"Spiking Neural Networks (SNNs) have gained great attraction due to their distinctive properties of low power consumption and fast inference on neuromorphic hardware. As the most effective method to get deep SNNs, ANN-SNN conversion has achieved comparable performance as ANNs on large-scale datasets. Despite this, it requires long time-steps to match the firing rates of SNNs to the activation of ANNs. As a result, the converted SNN suffers severe performance degradation problems with short time-steps, which hamper the practical application of SNNs. In this paper, we theoretically analyze ANN-SNN conversion error and derive the estimated activation function of SNNs. Then we propose the quantization clip-floor-shift activation function to replace the ReLU activation function in source ANNs, which can better approximate the activation function of SNNs. We prove that the expected conversion error between SNNs and ANNs is zero, enabling us to achieve high-accuracy and ultra-low-latency SNNs. We evaluate our method on CIFAR-10/100 and ImageNet datasets, and show that it outperforms the state-of-the-art ANN-SNN and directly trained SNNs in both accuracy and time-steps. To the best of our knowledge, this is the first time to explore high-performance ANN-SNN conversion with ultra-low latency (4 time-steps). Code is available at https://github.com/putshua/SNN\\_conversion\\_QCFS","url_abs":"https://arxiv.org/abs/2303.04347v1","url_pdf":"https://arxiv.org/pdf/2303.04347v1.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":"optimal-ann-snn-conversion-for-high-accuracy-1","repo_url":"https://github.com/putshua/SNN_conversion_QCFS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"optimal-ann-snn-conversion-for-high-accuracy-1","repo_url":"https://github.com/chenlicodebank/dynamic-confidence-in-spiking-neural-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.04347","atlas_url":"https://app.syntology.ai/?focus=2303.04347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04347"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/putshua/SNN_conversion_QCFS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenlicodebank/dynamic-confidence-in-spiking-neural-networks","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"6264802109c28063","entry":"forward","repo":"chenlicodebank/dynamic-confidence-in-spiking-neural-networks","repo_kind":"listed","path":"all_models.py","file_url":"https://github.com/chenlicodebank/dynamic-confidence-in-spiking-neural-networks/blob/HEAD/all_models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6264802109c28063"}},{"code_sha256_prefix":"015714df7a76b838","entry":"forward2","repo":"chenlicodebank/dynamic-confidence-in-spiking-neural-networks","repo_kind":"listed","path":"all_models.py","file_url":"https://github.com/chenlicodebank/dynamic-confidence-in-spiking-neural-networks/blob/HEAD/all_models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"015714df7a76b838"}},{"code_sha256_prefix":"0b677064ed40d42a","entry":"get_constraint","repo":"chenlicodebank/dynamic-confidence-in-spiking-neural-networks","repo_kind":"listed","path":"all_models.py","file_url":"https://github.com/chenlicodebank/dynamic-confidence-in-spiking-neural-networks/blob/HEAD/all_models.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0b677064ed40d42a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}