{"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/vssd-vision-mamba-with-non-casual-state-space","title":"VSSD: Vision Mamba with Non-Causal State Space Duality","arxiv_id":"2407.18559","date":"2024-07-26","proceeding":null,"authors":["Yuheng Shi","Minjing Dong","Mingjia Li","Chang Xu"],"abstract":"Vision transformers have significantly advanced the field of computer vision, offering robust modeling capabilities and global receptive field. However, their high computational demands limit their applicability in processing long sequences. To tackle this issue, State Space Models (SSMs) have gained prominence in vision tasks as they offer linear computational complexity. Recently, State Space Duality (SSD), an improved variant of SSMs, was introduced in Mamba2 to enhance model performance and efficiency. However, the inherent causal nature of SSD/SSMs restricts their applications in non-causal vision tasks. To address this limitation, we introduce Visual State Space Duality (VSSD) model, which has a non-causal format of SSD. Specifically, we propose to discard the magnitude of interactions between the hidden state and tokens while preserving their relative weights, which relieves the dependencies of token contribution on previous tokens. Together with the involvement of multi-scan strategies, we show that the scanning results can be integrated to achieve non-causality, which not only improves the performance of SSD in vision tasks but also enhances its efficiency. We conduct extensive experiments on various benchmarks including image classification, detection, and segmentation, where VSSD surpasses existing state-of-the-art SSM-based models. Code and weights are available at \\url{https://github.com/YuHengsss/VSSD}.","url_abs":"https://arxiv.org/abs/2407.18559v2","url_pdf":"https://arxiv.org/pdf/2407.18559v2.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":"vssd-vision-mamba-with-non-casual-state-space","repo_url":"https://github.com/yuhengsss/vssd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"vssd-vision-mamba-with-non-casual-state-space","repo_url":"https://github.com/YuHengsss/Trident","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"state-space-models","task_name":"State Space Models"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"non-maximum-suppression","method_name":"Non Maximum Suppression"},{"method_slug":"ssd","method_name":"SSD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.18559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18559"}},"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/yuhengsss/vssd","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YuHengsss/Trident","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":1,"ran_draft_wrong":3,"unverified":7},"by_repo_kind":{"listed":{"samples":10,"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":1,"samples":[{"code_sha256_prefix":"f19962ebb134b3d7","entry":"convert_to_custom_text_state_dict","repo":"YuHengsss/Trident","repo_kind":"listed","path":"open_clip/model.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/open_clip/model.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f19962ebb134b3d7"}},{"code_sha256_prefix":"dcd422d66b0581d8","entry":"get_cast_dtype","repo":"YuHengsss/Trident","repo_kind":"listed","path":"open_clip/model.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8"}},{"code_sha256_prefix":"b476c8cfbf0f1f47","entry":"get_input_dtype","repo":"YuHengsss/Trident","repo_kind":"listed","path":"open_clip/model.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/open_clip/model.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":"b476c8cfbf0f1f47"}},{"code_sha256_prefix":"5315806d8b42f938","entry":"import_abspy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"5315806d8b42f938"}},{"code_sha256_prefix":"ddcbd45e940484ee","entry":"gather_features","repo":"YuHengsss/Trident","repo_kind":"listed","path":"open_clip/loss.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/open_clip/loss.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":"ddcbd45e940484ee"}},{"code_sha256_prefix":"54731d24b3557840","entry":"get_cls_idx","repo":"YuHengsss/Trident","repo_kind":"listed","path":"trident.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/trident.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":"54731d24b3557840"}},{"code_sha256_prefix":"e332856e3c2fc814","entry":"neighbour_exchange","repo":"YuHengsss/Trident","repo_kind":"listed","path":"open_clip/loss.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/open_clip/loss.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":"e332856e3c2fc814"}},{"code_sha256_prefix":"5b1fd364afcf3c05","entry":"neighbour_exchange_bidir","repo":"YuHengsss/Trident","repo_kind":"listed","path":"open_clip/loss.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/open_clip/loss.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":"5b1fd364afcf3c05"}},{"code_sha256_prefix":"fb651d0a97fd4d3f","entry":"prepare_inputs_for_generation","repo":"YuHengsss/Trident","repo_kind":"listed","path":"open_clip/coca_model.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/open_clip/coca_model.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":"fb651d0a97fd4d3f"}},{"code_sha256_prefix":"2a377da4a76a2d44","entry":"register_pooler","repo":"YuHengsss/Trident","repo_kind":"listed","path":"open_clip/hf_model.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/open_clip/hf_model.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":"2a377da4a76a2d44"}},{"code_sha256_prefix":"7a6a3a7159d16d1f","entry":"show_mask","repo":"YuHengsss/Trident","repo_kind":"listed","path":"trident_demo.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/trident_demo.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":"7a6a3a7159d16d1f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}