{"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/exploring-feature-self-relation-for-self","title":"SERE: Exploring Feature Self-relation for Self-supervised Transformer","arxiv_id":"2206.05184","date":"2022-06-10","proceeding":null,"authors":["Zhong-Yu Li","ShangHua Gao","Ming-Ming Cheng"],"abstract":"Learning representations with self-supervision for convolutional networks (CNN) has been validated to be effective for vision tasks. As an alternative to CNN, vision transformers (ViT) have strong representation ability with spatial self-attention and channel-level feedforward networks. Recent works reveal that self-supervised learning helps unleash the great potential of ViT. Still, most works follow self-supervised strategies designed for CNN, e.g., instance-level discrimination of samples, but they ignore the properties of ViT. We observe that relational modeling on spatial and channel dimensions distinguishes ViT from other networks. To enforce this property, we explore the feature SElf-RElation (SERE) for training self-supervised ViT. Specifically, instead of conducting self-supervised learning solely on feature embeddings from multiple views, we utilize the feature self-relations, i.e., spatial/channel self-relations, for self-supervised learning. Self-relation based learning further enhances the relation modeling ability of ViT, resulting in stronger representations that stably improve performance on multiple downstream tasks. Our source code is publicly available at: https://github.com/MCG-NKU/SERE.","url_abs":"https://arxiv.org/abs/2206.05184v3","url_pdf":"https://arxiv.org/pdf/2206.05184v3.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":"exploring-feature-self-relation-for-self","repo_url":"https://github.com/MCG-NKU/SERE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-imagenet-s","task":"Semantic Segmentation","dataset":"ImageNet-S","model":"SERE (ViT-B/16, 100ep, 224x224, SSL+FT)","rank_in_archive_order":2,"of":20,"metrics":{"mIoU (test)":"63.3","mIoU (val)":"63.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-imagenet-s","task":"Semantic Segmentation","dataset":"ImageNet-S","model":"SERE (ViT-S/16, 100ep, 224x224, SSL+FT, mmseg)","rank_in_archive_order":6,"of":20,"metrics":{"mIoU (test)":"59.0","mIoU (val)":"59.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-imagenet-s","task":"Semantic Segmentation","dataset":"ImageNet-S","model":"SERE (ViT-S/16, 100ep, 224x224, SSL+FT)","rank_in_archive_order":7,"of":20,"metrics":{"mIoU (test)":"57.8","mIoU (val)":"58.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-imagenet-s","task":"Semantic Segmentation","dataset":"ImageNet-S","model":"SERE (ViT-B/16, 100ep, 224x224, SSL)","rank_in_archive_order":12,"of":20,"metrics":{"mIoU (test)":"48.2","mIoU (val)":"48.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-imagenet-s","task":"Semantic Segmentation","dataset":"ImageNet-S","model":"SERE (ViT-S/16, 100ep, 224x224, SSL, mmseg)","rank_in_archive_order":15,"of":20,"metrics":{"mIoU (test)":"40.5","mIoU (val)":"41.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-imagenet-s","task":"Semantic Segmentation","dataset":"ImageNet-S","model":"SERE (ViT-S/16, 100ep, 224x224, SSL)","rank_in_archive_order":16,"of":20,"metrics":{"mIoU (test)":"40.2","mIoU (val)":"41.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.05184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05184"}},"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/MCG-NKU/SERE","reach":null}],"summary":{"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":2,"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":3,"samples":[{"code_sha256_prefix":"55120f2026b56aa2","entry":"drop_path","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"code_sha256_prefix":"441e68b6af63085e","entry":"sampling","repo":"MCG-NKU/SERE","repo_kind":"official","path":"main_sere.py","file_url":"https://github.com/MCG-NKU/SERE/blob/HEAD/main_sere.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"441e68b6af63085e"}},{"code_sha256_prefix":"08a2dfd415ba7afb","entry":"sere_loss_pixel","repo":"MCG-NKU/SERE","repo_kind":"official","path":"main_sere.py","file_url":"https://github.com/MCG-NKU/SERE/blob/HEAD/main_sere.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"08a2dfd415ba7afb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}