{"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/mambavision-a-hybrid-mamba-transformer-vision","title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone","arxiv_id":"2407.08083","date":"2024-07-10","proceeding":"CVPR 2025 1","authors":["Ali Hatamizadeh","Jan Kautz"],"abstract":"We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. Through a comprehensive ablation study, we demonstrate the feasibility of integrating Vision Transformers (ViT) with Mamba. Our results show that equipping the Mamba architecture with self-attention blocks in the final layers greatly improves its capacity to capture long-range spatial dependencies. Based on these findings, we introduce a family of MambaVision models with a hierarchical architecture to meet various design criteria. For classification on the ImageNet-1K dataset, MambaVision variants achieve state-of-the-art (SOTA) performance in terms of both Top-1 accuracy and throughput. In downstream tasks such as object detection, instance segmentation, and semantic segmentation on MS COCO and ADE20K datasets, MambaVision outperforms comparably sized backbones while demonstrating favorable performance. Code: https://github.com/NVlabs/MambaVision","url_abs":"https://arxiv.org/abs/2407.08083v2","url_pdf":"https://arxiv.org/pdf/2407.08083v2.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":"mambavision-a-hybrid-mamba-transformer-vision","repo_url":"https://github.com/nvlabs/mambavision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"mambavision-a-hybrid-mamba-transformer-vision","repo_url":"https://github.com/hashmatshadab/mambarobustness","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"mambavision-a-hybrid-mamba-transformer-vision","repo_url":"https://github.com/jiaowoguanren0615/MambaVision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"mamba","task_name":"Mamba"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MambaVision-L3","rank_in_archive_order":58,"of":1060,"metrics":{"GFLOPs":"489.1","Top 1 Accuracy":"88.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MambaVision-L","rank_in_archive_order":271,"of":1060,"metrics":{"GFLOPs":"34.9","Number of params":"227.9M","Top 1 Accuracy":"85%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MambaVision-B","rank_in_archive_order":343,"of":1060,"metrics":{"GFLOPs":"15","Number of params":"97.7M","Top 1 Accuracy":"84.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MambaVision-S","rank_in_archive_order":445,"of":1060,"metrics":{"GFLOPs":"7.5","Number of params":"50.1M","Top 1 Accuracy":"83.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MambaVision-T2","rank_in_archive_order":514,"of":1060,"metrics":{"GFLOPs":"5.1","Number of params":"35.1M","Top 1 Accuracy":"82.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MambaVision-T","rank_in_archive_order":554,"of":1060,"metrics":{"GFLOPs":"4.4","Number of params":"31.8M","Top 1 Accuracy":"82.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MambaVision-L2","rank_in_archive_order":1057,"of":1060,"metrics":{"Number of params":"241.5M"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.08083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08083"}},"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/hashmatshadab/mambarobustness","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiaowoguanren0615/MambaVision","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvlabs/mambavision","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":1,"ran_fixture":1,"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":1,"repositories":1},"listed":{"samples":2,"ran":1,"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":6,"samples":[{"code_sha256_prefix":"9774a9d2355fe421","entry":"register_pip_model","repo":"nvlabs/mambavision","repo_kind":"official","path":"mambavision/models/registry.py","file_url":"https://github.com/nvlabs/mambavision/blob/HEAD/mambavision/models/registry.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9774a9d2355fe421"}},{"code_sha256_prefix":"88bf73966cf30ec8","entry":"window_partition","repo":"jiaowoguanren0615/MambaVision","repo_kind":"listed","path":"models/build_cls_models.py","file_url":"https://github.com/jiaowoguanren0615/MambaVision/blob/HEAD/models/build_cls_models.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88bf73966cf30ec8"}},{"code_sha256_prefix":"849e053052794bfb","entry":"create_scheduler","repo":"nvlabs/mambavision","repo_kind":"official","path":"mambavision/scheduler/scheduler_factory.py","file_url":"https://github.com/nvlabs/mambavision/blob/HEAD/mambavision/scheduler/scheduler_factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"849e053052794bfb"}},{"code_sha256_prefix":"cd2a47ded9dd84cf","entry":"is_model","repo":"nvlabs/mambavision","repo_kind":"official","path":"mambavision/models/registry.py","file_url":"https://github.com/nvlabs/mambavision/blob/HEAD/mambavision/models/registry.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd2a47ded9dd84cf"}},{"code_sha256_prefix":"d14a6ca5ff9d530e","entry":"list_models","repo":"nvlabs/mambavision","repo_kind":"official","path":"mambavision/models/registry.py","file_url":"https://github.com/nvlabs/mambavision/blob/HEAD/mambavision/models/registry.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d14a6ca5ff9d530e"}},{"code_sha256_prefix":"9ca6ef803df4e229","entry":"validate","repo":"nvlabs/mambavision","repo_kind":"official","path":"mambavision/validate_pip_model.py","file_url":"https://github.com/nvlabs/mambavision/blob/HEAD/mambavision/validate_pip_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9ca6ef803df4e229"}},{"code_sha256_prefix":"d432daacdf9484ff","entry":"validate","repo":"nvlabs/mambavision","repo_kind":"official","path":"mambavision/validate.py","file_url":"https://github.com/nvlabs/mambavision/blob/HEAD/mambavision/validate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d432daacdf9484ff"}},{"code_sha256_prefix":"578f68a6dc6b6dbe","entry":"window_reverse","repo":"jiaowoguanren0615/MambaVision","repo_kind":"listed","path":"models/build_cls_models.py","file_url":"https://github.com/jiaowoguanren0615/MambaVision/blob/HEAD/models/build_cls_models.py","link_basis":"first_harvest_node","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":"578f68a6dc6b6dbe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}