{"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/s-2-mlpv2-improved-spatial-shift-mlp","title":"S$^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision","arxiv_id":"2108.01072","date":"2021-08-02","proceeding":null,"authors":["Tan Yu","Xu Li","Yunfeng Cai","Mingming Sun","Ping Li"],"abstract":"Recently, MLP-based vision backbones emerge. MLP-based vision architectures with less inductive bias achieve competitive performance in image recognition compared with CNNs and vision Transformers. Among them, spatial-shift MLP (S$^2$-MLP), adopting the straightforward spatial-shift operation, achieves better performance than the pioneering works including MLP-mixer and ResMLP. More recently, using smaller patches with a pyramid structure, Vision Permutator (ViP) and Global Filter Network (GFNet) achieve better performance than S$^2$-MLP. In this paper, we improve the S$^2$-MLP vision backbone. We expand the feature map along the channel dimension and split the expanded feature map into several parts. We conduct different spatial-shift operations on split parts. Meanwhile, we exploit the split-attention operation to fuse these split parts. Moreover, like the counterparts, we adopt smaller-scale patches and use a pyramid structure for boosting the image recognition accuracy. We term the improved spatial-shift MLP vision backbone as S$^2$-MLPv2. Using 55M parameters, our medium-scale model, S$^2$-MLPv2-Medium achieves an $83.6\\%$ top-1 accuracy on the ImageNet-1K benchmark using $224\\times 224$ images without self-attention and external training data.","url_abs":"https://arxiv.org/abs/2108.01072v1","url_pdf":"https://arxiv.org/pdf/2108.01072v1.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":"s-2-mlpv2-improved-spatial-shift-mlp","repo_url":"https://github.com/liuruiyang98/Jittor-MLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"s-2-mlpv2-improved-spatial-shift-mlp","repo_url":"https://github.com/dslisleedh/MLP_based_models-flax/blob/main/s2mlpv2.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"s-2-mlpv2-improved-spatial-shift-mlp","repo_url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/S2Attention.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[{"method_slug":"affine-operator","method_name":"Affine Operator"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"mlp-mixer","method_name":"MLP-Mixer"},{"method_slug":"resmlp","method_name":"ResMLP"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.01072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.01072"}},"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/liuruiyang98/Jittor-MLP","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dslisleedh/MLP_based_models-flax/blob/main/s2mlpv2.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/S2Attention.py","reach":null}],"summary":{"ran_fixture":4},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"017854db0c4ab907","entry":"spatial_shift1","repo":"liuruiyang98/Jittor-MLP","repo_kind":"listed","path":"models_jittor/s2_mlp_v2.py","file_url":"https://github.com/liuruiyang98/Jittor-MLP/blob/HEAD/models_jittor/s2_mlp_v2.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":"017854db0c4ab907"}},{"code_sha256_prefix":"8abeb37d41f3b6fa","entry":"spatial_shift1","repo":"dslisleedh/MLP_based_models-flax","repo_kind":"listed","path":"s2mlpv2.py","file_url":"https://github.com/dslisleedh/MLP_based_models-flax/blob/HEAD/s2mlpv2.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8abeb37d41f3b6fa"}},{"code_sha256_prefix":"1825e2274eae2758","entry":"spatial_shift2","repo":"liuruiyang98/Jittor-MLP","repo_kind":"listed","path":"models_jittor/s2_mlp_v2.py","file_url":"https://github.com/liuruiyang98/Jittor-MLP/blob/HEAD/models_jittor/s2_mlp_v2.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":"1825e2274eae2758"}},{"code_sha256_prefix":"aef82f3679df0048","entry":"spatial_shift2","repo":"dslisleedh/MLP_based_models-flax","repo_kind":"listed","path":"s2mlpv2.py","file_url":"https://github.com/dslisleedh/MLP_based_models-flax/blob/HEAD/s2mlpv2.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aef82f3679df0048"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}