{"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/iformer-integrating-convnet-and-transformer","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","arxiv_id":"2501.15369","date":"2025-01-26","proceeding":null,"authors":["Chuanyang Zheng"],"abstract":"We present a new family of mobile hybrid vision networks, called iFormer, with a focus on optimizing latency and accuracy on mobile applications. iFormer effectively integrates the fast local representation capacity of convolution with the efficient global modeling ability of self-attention. The local interactions are derived from transforming a standard convolutional network, \\textit{i.e.}, ConvNeXt, to design a more lightweight mobile network. Our newly introduced mobile modulation attention removes memory-intensive operations in MHA and employs an efficient modulation mechanism to boost dynamic global representational capacity. We conduct comprehensive experiments demonstrating that iFormer outperforms existing lightweight networks across various tasks. Notably, iFormer achieves an impressive Top-1 accuracy of 80.4\\% on ImageNet-1k with a latency of only 1.10 ms on an iPhone 13, surpassing the recently proposed MobileNetV4 under similar latency constraints. Additionally, our method shows significant improvements in downstream tasks, including COCO object detection, instance segmentation, and ADE20k semantic segmentation, while still maintaining low latency on mobile devices for high-resolution inputs in these scenarios.","url_abs":"https://arxiv.org/abs/2501.15369v1","url_pdf":"https://arxiv.org/pdf/2501.15369v1.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":"iformer-integrating-convnet-and-transformer","repo_url":"https://github.com/chuanyangzheng/iformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"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":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"convnext","method_name":"ConvNeXt"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.15369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15369"}},"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":"deterministic:regex_extraction","url":"https://github.com/ChuanyangZheng/iFormer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chuanyangzheng/iformer","reach":null}],"summary":{"ran":4,"ran_fixture":1,"unverified":5},"by_repo_kind":{"official":{"samples":8,"ran":5,"repositories":1},"community":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"00bd980cb0c92bbc","entry":"BN_Linear","repo":"chuanyangzheng/iformer","repo_kind":"official","path":"models/iformer.py","file_url":"https://github.com/chuanyangzheng/iformer/blob/HEAD/models/iformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00bd980cb0c92bbc"}},{"code_sha256_prefix":"be930a9ccda0b4c9","entry":"Classfier","repo":"chuanyangzheng/iformer","repo_kind":"official","path":"models/iformer.py","file_url":"https://github.com/chuanyangzheng/iformer/blob/HEAD/models/iformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be930a9ccda0b4c9"}},{"code_sha256_prefix":"1adb071078d6909f","entry":"Conv2d_BN","repo":"chuanyangzheng/iformer","repo_kind":"official","path":"models/iformer.py","file_url":"https://github.com/chuanyangzheng/iformer/blob/HEAD/models/iformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1adb071078d6909f"}},{"code_sha256_prefix":"fc32f0783a025e82","entry":"EdgeResidual","repo":"chuanyangzheng/iformer","repo_kind":"official","path":"models/iformer.py","file_url":"https://github.com/chuanyangzheng/iformer/blob/HEAD/models/iformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc32f0783a025e82"}},{"code_sha256_prefix":"7a3f740ecc375589","entry":"window_partition","repo":"ChuanyangZheng/iFormer","repo_kind":"official","path":"detection/iformer.py","file_url":"https://github.com/ChuanyangZheng/iFormer/blob/HEAD/detection/iformer.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":"7a3f740ecc375589"}},{"code_sha256_prefix":"ffef9979cc983271","entry":"BasicBlock","repo":"chuanyangzheng/iformer","repo_kind":"official","path":"models/iformer.py","file_url":"https://github.com/chuanyangzheng/iformer/blob/HEAD/models/iformer.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":"ffef9979cc983271"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"sail-sg/iFormer","repo_kind":"community","path":"fine-tune.py","file_url":"https://github.com/sail-sg/iFormer/blob/HEAD/fine-tune.py","link_basis":"first_harvest_node","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":"73cecca9f3575f09"}},{"code_sha256_prefix":"5931f19101efb167","entry":"iFormer","repo":"chuanyangzheng/iformer","repo_kind":"official","path":"models/iformer.py","file_url":"https://github.com/chuanyangzheng/iformer/blob/HEAD/models/iformer.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":"5931f19101efb167"}},{"code_sha256_prefix":"e2a98c6a53ded11f","entry":"validate","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"e2a98c6a53ded11f"}},{"code_sha256_prefix":"7f2b1f05bf53f1b7","entry":"window_reverse","repo":"ChuanyangZheng/iFormer","repo_kind":"official","path":"detection/iformer.py","file_url":"https://github.com/ChuanyangZheng/iFormer/blob/HEAD/detection/iformer.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":"7f2b1f05bf53f1b7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}