{"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/edgeformer-improving-light-weight-convnets-by","title":"ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer","arxiv_id":"2203.03952","date":"2022-03-08","proceeding":null,"authors":["Haokui Zhang","Wenze Hu","Xiaoyu Wang"],"abstract":"Recently, vision transformers started to show impressive results which outperform large convolution based models significantly. However, in the area of small models for mobile or resource constrained devices, ConvNet still has its own advantages in both performance and model complexity. We propose ParC-Net, a pure ConvNet based backbone model that further strengthens these advantages by fusing the merits of vision transformers into ConvNets. Specifically, we propose position aware circular convolution (ParC), a light-weight convolution op which boasts a global receptive field while producing location sensitive features as in local convolutions. We combine the ParCs and squeeze-exictation ops to form a meta-former like model block, which further has the attention mechanism like transformers. The aforementioned block can be used in plug-and-play manner to replace relevant blocks in ConvNets or transformers. Experiment results show that the proposed ParC-Net achieves better performance than popular light-weight ConvNets and vision transformer based models in common vision tasks and datasets, while having fewer parameters and faster inference speed. For classification on ImageNet-1k, ParC-Net achieves 78.6% top-1 accuracy with about 5.0 million parameters, saving 11% parameters and 13% computational cost but gaining 0.2% higher accuracy and 23% faster inference speed (on ARM based Rockchip RK3288) compared with MobileViT, and uses only 0.5 times parameters but gaining 2.7% accuracy compared with DeIT. On MS-COCO object detection and PASCAL VOC segmentation tasks, ParC-Net also shows better performance. Source code is available at https://github.com/hkzhang91/ParC-Net","url_abs":"https://arxiv.org/abs/2203.03952v5","url_pdf":"https://arxiv.org/pdf/2203.03952v5.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":"edgeformer-improving-light-weight-convnets-by","repo_url":"https://github.com/hkzhang91/edgeformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"edgeformer-improving-light-weight-convnets-by","repo_url":"https://github.com/hkzhang91/pacc-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"edgeformer-improving-light-weight-convnets-by","repo_url":"https://github.com/hkzhang91/parc-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":null,"task_name":"Position"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"aware","method_name":"AWARE"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mobilevit","method_name":"MobileViT"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"EdgeFormer-S","rank_in_archive_order":816,"of":1060,"metrics":{"GFLOPs":"3.48","Number of params":"5M","Top 1 Accuracy":"78.63%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.03952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03952"}},"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/hkzhang91/edgeformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hkzhang91/parc-net","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hkzhang91/pacc-net","reach":null}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":3}},"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":5,"samples":[{"code_sha256_prefix":"bf2ef049fe8a2900","entry":"BaseModule","repo":"hkzhang91/parc-net","repo_kind":"official","path":"cvnets/modules/edgeformer_block.py","file_url":"https://github.com/hkzhang91/parc-net/blob/HEAD/cvnets/modules/edgeformer_block.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf2ef049fe8a2900"}},{"code_sha256_prefix":"7466f7df30d27f91","entry":"Dropout","repo":"hkzhang91/parc-net","repo_kind":"official","path":"cvnets/modules/edgeformer_block.py","file_url":"https://github.com/hkzhang91/parc-net/blob/HEAD/cvnets/modules/edgeformer_block.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7466f7df30d27f91"}},{"code_sha256_prefix":"52455487af0ae043","entry":"ParC_operator","repo":"hkzhang91/edgeformer","repo_kind":"official","path":"ParC_ConvNets/ParC_convnext.py","file_url":"https://github.com/hkzhang91/edgeformer/blob/HEAD/ParC_ConvNets/ParC_convnext.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52455487af0ae043"}},{"code_sha256_prefix":"6ec2dca9fc2e72d1","entry":"ParC_operator","repo":"hkzhang91/pacc-net","repo_kind":"official","path":"ParC_ConvNets/ParC_resnet50.py","file_url":"https://github.com/hkzhang91/pacc-net/blob/HEAD/ParC_ConvNets/ParC_resnet50.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ec2dca9fc2e72d1"}},{"code_sha256_prefix":"937c1e069ff4b33a","entry":"gcc_mf_block","repo":"hkzhang91/parc-net","repo_kind":"official","path":"cvnets/modules/edgeformer_block.py","file_url":"https://github.com/hkzhang91/parc-net/blob/HEAD/cvnets/modules/edgeformer_block.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"937c1e069ff4b33a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}