{"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/rf-next-efficient-receptive-field-search-for","title":"RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks","arxiv_id":"2206.06637","date":"2022-06-14","proceeding":null,"authors":["ShangHua Gao","Zhong-Yu Li","Qi Han","Ming-Ming Cheng","Liang Wang"],"abstract":"Temporal/spatial receptive fields of models play an important role in sequential/spatial tasks. Large receptive fields facilitate long-term relations, while small receptive fields help to capture the local details. Existing methods construct models with hand-designed receptive fields in layers. Can we effectively search for receptive field combinations to replace hand-designed patterns? To answer this question, we propose to find better receptive field combinations through a global-to-local search scheme. Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combinations further. The global search finds possible coarse combinations other than human-designed patterns. On top of the global search, we propose an expectation-guided iterative local search scheme to refine combinations effectively. Our RF-Next models, plugging receptive field search to various models, boost the performance on many tasks, e.g., temporal action segmentation, object detection, instance segmentation, and speech synthesis. The source code is publicly available on http://mmcheng.net/rfnext.","url_abs":"https://arxiv.org/abs/2206.06637v2","url_pdf":"https://arxiv.org/pdf/2206.06637v2.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":"rf-next-efficient-receptive-field-search-for","repo_url":"https://github.com/ShangHua-Gao/RFNext","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"rf-next-efficient-receptive-field-search-for","repo_url":"https://github.com/ShangHua-Gao/G2L-search","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"temporal-action-segmentation","task_name":"Temporal Action Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset":"Breakfast","model":"RF++-SSTDA","rank_in_archive_order":33,"of":37,"metrics":{"Acc":"70.8"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco-2017-val","task":"Instance Segmentation","dataset":"COCO 2017 val","model":"RF-ConvNeXt-T Cascade R-CNN","rank_in_archive_order":4,"of":4,"metrics":{"AP":"44.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-2017-val","task":"Object Detection","dataset":"COCO 2017 val","model":"RF-ConvNeXt-T Cascade R-CNN","rank_in_archive_order":15,"of":33,"metrics":{"AP":"50.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-imagenet-s","task":"Semantic Segmentation","dataset":"ImageNet-S","model":"RF-ConvNext-Tiny (rfmerge, P4, 224x224, SUP)","rank_in_archive_order":8,"of":20,"metrics":{"mIoU (test)":"51.1","mIoU (val)":"51.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-imagenet-s","task":"Semantic Segmentation","dataset":"ImageNet-S","model":"RF-ConvNext-Tiny (rfmultiple, P4, 224x224, SUP)","rank_in_archive_order":9,"of":20,"metrics":{"mIoU (test)":"50.5","mIoU (val)":"50.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-imagenet-s","task":"Semantic Segmentation","dataset":"ImageNet-S","model":"RF-ConvNext-Tiny (rfsingle, P4, 224x224, SUP)","rank_in_archive_order":10,"of":20,"metrics":{"mIoU (test)":"50.5","mIoU (val)":"50.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.06637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06637"}},"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/ShangHua-Gao/G2L-search","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShangHua-Gao/RFNext","reach":null}],"summary":{"ran_fixture":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"25cf94f18618b3d7","entry":"rf_expand","repo":"ShangHua-Gao/RFNext","repo_kind":"official","path":"rfconv.py","file_url":"https://github.com/ShangHua-Gao/RFNext/blob/HEAD/rfconv.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"25cf94f18618b3d7"}},{"code_sha256_prefix":"0c954bb3b69b23b0","entry":"value_crop","repo":"ShangHua-Gao/RFNext","repo_kind":"official","path":"rfconv.py","file_url":"https://github.com/ShangHua-Gao/RFNext/blob/HEAD/rfconv.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c954bb3b69b23b0"}},{"code_sha256_prefix":"262171d3c132d5b4","entry":"checkpoint_filter_fn","repo":"ShangHua-Gao/RFNext","repo_kind":"official","path":"rfconvnext.py","file_url":"https://github.com/ShangHua-Gao/RFNext/blob/HEAD/rfconvnext.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"262171d3c132d5b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}