{"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/mixformer-mixing-features-across-windows-and","title":"MixFormer: Mixing Features across Windows and Dimensions","arxiv_id":"2204.02557","date":"2022-04-06","proceeding":"CVPR 2022 1","authors":["Qiang Chen","Qiman Wu","Jian Wang","Qinghao Hu","Tao Hu","Errui Ding","Jian Cheng","Jingdong Wang"],"abstract":"While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares weights on the channel dimension. We propose MixFormer to find a solution. First, we combine local-window self-attention with depth-wise convolution in a parallel design, modeling cross-window connections to enlarge the receptive fields. Second, we propose bi-directional interactions across branches to provide complementary clues in the channel and spatial dimensions. These two designs are integrated to achieve efficient feature mixing among windows and dimensions. Our MixFormer provides competitive results on image classification with EfficientNet and shows better results than RegNet and Swin Transformer. Performance in downstream tasks outperforms its alternatives by significant margins with less computational costs in 5 dense prediction tasks on MS COCO, ADE20k, and LVIS. Code is available at \\url{https://github.com/PaddlePaddle/PaddleClas}.","url_abs":"https://arxiv.org/abs/2204.02557v2","url_pdf":"https://arxiv.org/pdf/2204.02557v2.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":"mixformer-mixing-features-across-windows-and","repo_url":"https://github.com/PaddlePaddle/PaddleClas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mixformer-mixing-features-across-windows-and","repo_url":"https://github.com/clearlon/stylemixformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mixformer-mixing-features-across-windows-and","repo_url":"https://github.com/flytocc/PaddleClas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"},{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"},{"method_slug":"swin-transformer","method_name":"Swin Transformer"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2204.02557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02557"}},"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/PaddlePaddle/PaddleClas","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clearlon/stylemixformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flytocc/PaddleClas","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":9},"by_repo_kind":{"listed":{"samples":14,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"5d037926d5843004","entry":"AttentionCC","repo":"clearlon/stylemixformer","repo_kind":"listed","path":"styleformer/archs/styleformer_util.py","file_url":"https://github.com/clearlon/stylemixformer/blob/HEAD/styleformer/archs/styleformer_util.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":"5d037926d5843004"}},{"code_sha256_prefix":"5e935e13456b2294","entry":"ChannelInteraction","repo":"clearlon/stylemixformer","repo_kind":"listed","path":"styleformer/archs/styleformer_util.py","file_url":"https://github.com/clearlon/stylemixformer/blob/HEAD/styleformer/archs/styleformer_util.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":"5e935e13456b2294"}},{"code_sha256_prefix":"05212f4e91896ff3","entry":"MixRestormer","repo":"clearlon/stylemixformer","repo_kind":"listed","path":"styleformer/archs/styleformer_util.py","file_url":"https://github.com/clearlon/stylemixformer/blob/HEAD/styleformer/archs/styleformer_util.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":"05212f4e91896ff3"}},{"code_sha256_prefix":"abc6ee09587fed69","entry":"SimpleGate","repo":"clearlon/stylemixformer","repo_kind":"listed","path":"styleformer/archs/styleformer_util.py","file_url":"https://github.com/clearlon/stylemixformer/blob/HEAD/styleformer/archs/styleformer_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"abc6ee09587fed69"}},{"code_sha256_prefix":"f21f09acc77e8d76","entry":"SpatialInteraction","repo":"clearlon/stylemixformer","repo_kind":"listed","path":"styleformer/archs/styleformer_util.py","file_url":"https://github.com/clearlon/stylemixformer/blob/HEAD/styleformer/archs/styleformer_util.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":"f21f09acc77e8d76"}},{"code_sha256_prefix":"fab16299446cee0f","entry":"check_model_file","repo":"flytocc/PaddleClas","repo_kind":"listed","path":"paddleclas.py","file_url":"https://github.com/flytocc/PaddleClas/blob/HEAD/paddleclas.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":"fab16299446cee0f"}},{"code_sha256_prefix":"bffab447a4eca741","entry":"cosine_similarity","repo":"flytocc/PaddleClas","repo_kind":"listed","path":"ppcls/loss/dist_loss.py","file_url":"https://github.com/flytocc/PaddleClas/blob/HEAD/ppcls/loss/dist_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":"bffab447a4eca741"}},{"code_sha256_prefix":"efe80a6faca7b66d","entry":"extract","repo":"flytocc/PaddleClas","repo_kind":"listed","path":"test_tipc/extract_loss.py","file_url":"https://github.com/flytocc/PaddleClas/blob/HEAD/test_tipc/extract_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":"efe80a6faca7b66d"}},{"code_sha256_prefix":"58f2b08eed947b76","entry":"inter_class_relation","repo":"flytocc/PaddleClas","repo_kind":"listed","path":"ppcls/loss/dist_loss.py","file_url":"https://github.com/flytocc/PaddleClas/blob/HEAD/ppcls/loss/dist_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":"58f2b08eed947b76"}},{"code_sha256_prefix":"413184c918d844c8","entry":"is_valid","repo":"flytocc/PaddleClas","repo_kind":"listed","path":"test_tipc/extract_loss.py","file_url":"https://github.com/flytocc/PaddleClas/blob/HEAD/test_tipc/extract_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":"413184c918d844c8"}},{"code_sha256_prefix":"a7997903cea7558c","entry":"pearson_correlation","repo":"flytocc/PaddleClas","repo_kind":"listed","path":"ppcls/loss/dist_loss.py","file_url":"https://github.com/flytocc/PaddleClas/blob/HEAD/ppcls/loss/dist_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":"a7997903cea7558c"}},{"code_sha256_prefix":"21421188135068e9","entry":"rerange_index","repo":"flytocc/PaddleClas","repo_kind":"listed","path":"ppcls/loss/comfunc.py","file_url":"https://github.com/flytocc/PaddleClas/blob/HEAD/ppcls/loss/comfunc.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":"21421188135068e9"}},{"code_sha256_prefix":"398221cc3d60f209","entry":"similar_model_names","repo":"flytocc/PaddleClas","repo_kind":"listed","path":"paddleclas.py","file_url":"https://github.com/flytocc/PaddleClas/blob/HEAD/paddleclas.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":"398221cc3d60f209"}},{"code_sha256_prefix":"0c3f60f3f5d20da9","entry":"unique_shape","repo":"flytocc/PaddleClas","repo_kind":"listed","path":"ppcls/loss/afdloss.py","file_url":"https://github.com/flytocc/PaddleClas/blob/HEAD/ppcls/loss/afdloss.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":"0c3f60f3f5d20da9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}