{"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/efficientvit-enhanced-linear-attention-for","title":"EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction","arxiv_id":"2205.14756","date":"2022-05-29","proceeding":null,"authors":["Han Cai","Junyan Li","Muyan Hu","Chuang Gan","Song Han"],"abstract":"High-resolution dense prediction enables many appealing real-world applications, such as computational photography, autonomous driving, etc. However, the vast computational cost makes deploying state-of-the-art high-resolution dense prediction models on hardware devices difficult. This work presents EfficientViT, a new family of high-resolution vision models with novel multi-scale linear attention. Unlike prior high-resolution dense prediction models that rely on heavy softmax attention, hardware-inefficient large-kernel convolution, or complicated topology structure to obtain good performances, our multi-scale linear attention achieves the global receptive field and multi-scale learning (two desirable features for high-resolution dense prediction) with only lightweight and hardware-efficient operations. As such, EfficientViT delivers remarkable performance gains over previous state-of-the-art models with significant speedup on diverse hardware platforms, including mobile CPU, edge GPU, and cloud GPU. Without performance loss on Cityscapes, our EfficientViT provides up to 13.9$\\times$ and 6.2$\\times$ GPU latency reduction over SegFormer and SegNeXt, respectively. For super-resolution, EfficientViT delivers up to 6.4x speedup over Restormer while providing 0.11dB gain in PSNR. For Segment Anything, EfficientViT delivers 48.9x higher throughput on A100 GPU while achieving slightly better zero-shot instance segmentation performance on COCO.","url_abs":"https://arxiv.org/abs/2205.14756v6","url_pdf":"https://arxiv.org/pdf/2205.14756v6.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":"efficientvit-enhanced-linear-attention-for","repo_url":"https://github.com/mit-han-lab/efficientvit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"efficientvit-enhanced-linear-attention-for","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"efficientvit-enhanced-linear-attention-for","repo_url":"https://github.com/2023-MindSpore-4/Code1/tree/main/Efficientnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"efficientvit-enhanced-linear-attention-for","repo_url":"https://github.com/2023-MindSpore-4/Code10/tree/main/Efficientnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"efficientvit-enhanced-linear-attention-for","repo_url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/efficientvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"efficientvit-enhanced-linear-attention-for","repo_url":"https://gitlab.com/birder/birder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"zero-shot-instance-segmentation","task_name":"Zero-Shot Instance Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"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":"mix-ffn","method_name":"Mix-FFN"},{"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":"segformer","method_name":"SegFormer"},{"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":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"EfficientViT-L2 (r384)","rank_in_archive_order":181,"of":1060,"metrics":{"GFLOPs":"20","Number of params":"64M","Top 1 Accuracy":"86%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"EfficientViT-L2 (r288)","rank_in_archive_order":215,"of":1060,"metrics":{"GFLOPs":"11","Number of params":"64M","Top 1 Accuracy":"85.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"EfficientViT-L1 (r224)","rank_in_archive_order":310,"of":1060,"metrics":{"GFLOPs":"5.3","Number of params":"53M","Top 1 Accuracy":"84.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"EfficientViT-B3 (r288)","rank_in_archive_order":337,"of":1060,"metrics":{"GFLOPs":"6.5","Number of params":"49M","Top 1 Accuracy":"84.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"EfficientViT-B3 (r224)","rank_in_archive_order":420,"of":1060,"metrics":{"GFLOPs":"4","Top 1 Accuracy":"83.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"EfficientViT-B2 (r256)","rank_in_archive_order":511,"of":1060,"metrics":{"GFLOPs":"2.1","Number of params":"24M","Top 1 Accuracy":"82.7%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"EfficientViT-B3 (r512)","rank_in_archive_order":142,"of":235,"metrics":{"Validation mIoU":"49"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"EfficientViT-B3 (r1184x2368)","rank_in_archive_order":27,"of":99,"metrics":{"mIoU":"83.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.14756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14756"}},"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/rwightman/pytorch-image-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/Efficientnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/efficientvit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mit-han-lab/efficientvit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitlab.com/birder/birder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code1/tree/main/Efficientnet","reach":null}],"summary":{"ran_honours":1,"ran_fixture":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"bb3d4f05a88ee013","entry":"load_image","repo":"mit-han-lab/efficientvit","repo_kind":"official","path":"applications/efficientvit_sam/demo_efficientvit_sam_model.py","file_url":"https://github.com/mit-han-lab/efficientvit/blob/HEAD/applications/efficientvit_sam/demo_efficientvit_sam_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb3d4f05a88ee013"}},{"code_sha256_prefix":"35931102182b33e8","entry":"accuracy","repo":"mit-han-lab/efficientvit","repo_kind":"official","path":"applications/efficientvit_cls/eval_efficientvit_cls_model.py","file_url":"https://github.com/mit-han-lab/efficientvit/blob/HEAD/applications/efficientvit_cls/eval_efficientvit_cls_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"35931102182b33e8"}},{"code_sha256_prefix":"799ae994e666d035","entry":"cat_images","repo":"mit-han-lab/efficientvit","repo_kind":"official","path":"applications/efficientvit_sam/demo_efficientvit_sam_model.py","file_url":"https://github.com/mit-han-lab/efficientvit/blob/HEAD/applications/efficientvit_sam/demo_efficientvit_sam_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"799ae994e666d035"}},{"code_sha256_prefix":"066e85f370a04fd7","entry":"draw_binary_mask","repo":"mit-han-lab/efficientvit","repo_kind":"official","path":"applications/efficientvit_sam/demo_efficientvit_sam_model.py","file_url":"https://github.com/mit-han-lab/efficientvit/blob/HEAD/applications/efficientvit_sam/demo_efficientvit_sam_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"066e85f370a04fd7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}