{"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/smpconv-self-moving-point-representations-for","title":"SMPConv: Self-moving Point Representations for Continuous Convolution","arxiv_id":"2304.02330","date":"2023-04-05","proceeding":"CVPR 2023 1","authors":["Sanghyeon Kim","Eunbyung Park"],"abstract":"Continuous convolution has recently gained prominence due to its ability to handle irregularly sampled data and model long-term dependency. Also, the promising experimental results of using large convolutional kernels have catalyzed the development of continuous convolution since they can construct large kernels very efficiently. Leveraging neural networks, more specifically multilayer perceptrons (MLPs), is by far the most prevalent approach to implementing continuous convolution. However, there are a few drawbacks, such as high computational costs, complex hyperparameter tuning, and limited descriptive power of filters. This paper suggests an alternative approach to building a continuous convolution without neural networks, resulting in more computationally efficient and improved performance. We present self-moving point representations where weight parameters freely move, and interpolation schemes are used to implement continuous functions. When applied to construct convolutional kernels, the experimental results have shown improved performance with drop-in replacement in the existing frameworks. Due to its lightweight structure, we are first to demonstrate the effectiveness of continuous convolution in a large-scale setting, e.g., ImageNet, presenting the improvements over the prior arts. Our code is available on https://github.com/sangnekim/SMPConv","url_abs":"https://arxiv.org/abs/2304.02330v1","url_pdf":"https://arxiv.org/pdf/2304.02330v1.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":"smpconv-self-moving-point-representations-for","repo_url":"https://github.com/sangnekim/smpconv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"sequential-image-classification","task_name":"Sequential Image Classification"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sequential-image-classification-on-sequential-1","task":"Sequential Image Classification","dataset":"Sequential CIFAR-10","model":"SMPConv","rank_in_archive_order":4,"of":13,"metrics":{"Unpermuted Accuracy":"84.86%"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-image-classification-on-sequential","task":"Sequential Image Classification","dataset":"Sequential MNIST","model":"SMPConv","rank_in_archive_order":1,"of":30,"metrics":{"Permuted Accuracy":"99.10","Unpermuted Accuracy":"99.75"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.02330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.02330"}},"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/sangnekim/smpconv","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/sangnekim/SMPConv","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":7},"by_repo_kind":{"official":{"samples":9,"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":0,"samples":[{"code_sha256_prefix":"6a0317bfd6be9557","entry":"build_transform","repo":"sangnekim/SMPConv","repo_kind":"official","path":"smp_imagenet/datasets.py","file_url":"https://github.com/sangnekim/SMPConv/blob/HEAD/smp_imagenet/datasets.py","link_basis":"harvester_set","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":"6a0317bfd6be9557"}},{"code_sha256_prefix":"b4613da968a83fc8","entry":"get_bn","repo":"sangnekim/SMPConv","repo_kind":"official","path":"smp_imagenet/models/SMPConv.py","file_url":"https://github.com/sangnekim/SMPConv/blob/HEAD/smp_imagenet/models/SMPConv.py","link_basis":"harvester_set","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":"b4613da968a83fc8"}},{"code_sha256_prefix":"fdbba1a8d4185180","entry":"build_dataset","repo":"sangnekim/SMPConv","repo_kind":"official","path":"smp_imagenet/datasets.py","file_url":"https://github.com/sangnekim/SMPConv/blob/HEAD/smp_imagenet/datasets.py","link_basis":"harvester_set","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":"fdbba1a8d4185180"}},{"code_sha256_prefix":"2733824f9727be2c","entry":"construct_optimizer","repo":"sangnekim/SMPConv","repo_kind":"official","path":"smp/optim.py","file_url":"https://github.com/sangnekim/SMPConv/blob/HEAD/smp/optim.py","link_basis":"harvester_set","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":"2733824f9727be2c"}},{"code_sha256_prefix":"b700fb0a3496b255","entry":"cosine_scheduler","repo":"sangnekim/SMPConv","repo_kind":"official","path":"smp_imagenet/utils.py","file_url":"https://github.com/sangnekim/SMPConv/blob/HEAD/smp_imagenet/utils.py","link_basis":"harvester_set","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":"b700fb0a3496b255"}},{"code_sha256_prefix":"6fcb986ae6d99a7d","entry":"evaluate","repo":"sangnekim/SMPConv","repo_kind":"official","path":"smp_imagenet/engine.py","file_url":"https://github.com/sangnekim/SMPConv/blob/HEAD/smp_imagenet/engine.py","link_basis":"harvester_set","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":"6fcb986ae6d99a7d"}},{"code_sha256_prefix":"bf7fe9b696b6d730","entry":"get_num_layer_for_convnext","repo":"sangnekim/SMPConv","repo_kind":"official","path":"smp_imagenet/optim_factory.py","file_url":"https://github.com/sangnekim/SMPConv/blob/HEAD/smp_imagenet/optim_factory.py","link_basis":"harvester_set","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":"bf7fe9b696b6d730"}},{"code_sha256_prefix":"f752c61c80d4fa81","entry":"get_parameter_groups","repo":"sangnekim/SMPConv","repo_kind":"official","path":"smp_imagenet/optim_factory.py","file_url":"https://github.com/sangnekim/SMPConv/blob/HEAD/smp_imagenet/optim_factory.py","link_basis":"harvester_set","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":"f752c61c80d4fa81"}},{"code_sha256_prefix":"c56d076c31646e95","entry":"rel_pos","repo":"sangnekim/SMPConv","repo_kind":"official","path":"smp_imagenet/models/SMPConv.py","file_url":"https://github.com/sangnekim/SMPConv/blob/HEAD/smp_imagenet/models/SMPConv.py","link_basis":"harvester_set","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":"c56d076c31646e95"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}