{"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/weakly-supervised-continual-learning","title":"Continual Semi-Supervised Learning through Contrastive Interpolation Consistency","arxiv_id":"2108.06552","date":"2021-08-14","proceeding":null,"authors":["Matteo Boschini","Pietro Buzzega","Lorenzo Bonicelli","Angelo Porrello","Simone Calderara"],"abstract":"Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks without incurring forgetting. CL settings proposed in literature assume that every incoming example is paired with ground-truth annotations. However, this clashes with many real-world applications: gathering labeled data, which is in itself tedious and expensive, becomes infeasible when data flow as a stream. This work explores Continual Semi-Supervised Learning (CSSL): here, only a small fraction of labeled input examples are shown to the learner. We assess how current CL methods (e.g.: EWC, LwF, iCaRL, ER, GDumb, DER) perform in this novel and challenging scenario, where overfitting entangles forgetting. Subsequently, we design a novel CSSL method that exploits metric learning and consistency regularization to leverage unlabeled examples while learning. We show that our proposal exhibits higher resilience to diminishing supervision and, even more surprisingly, relying only on 25% supervision suffices to outperform SOTA methods trained under full supervision.","url_abs":"https://arxiv.org/abs/2108.06552v3","url_pdf":"https://arxiv.org/pdf/2108.06552v3.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":"weakly-supervised-continual-learning","repo_url":"https://github.com/loribonna/cssl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"weakly-supervised-continual-learning","repo_url":"https://github.com/aimagelab/mammoth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[{"method_slug":"ewc","method_name":"EWC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.06552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.06552"}},"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/aimagelab/mammoth","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/loribonna/cssl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":5},"by_repo_kind":{"official":{"samples":7,"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":"e3d484150b4f907c","entry":"modified_kl_div","repo":"loribonna/cssl","repo_kind":"official","path":"models/lwf.py","file_url":"https://github.com/loribonna/cssl/blob/HEAD/models/lwf.py","link_basis":"plan_row","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":"e3d484150b4f907c"}},{"code_sha256_prefix":"bc5d184387cac930","entry":"smooth","repo":"loribonna/cssl","repo_kind":"official","path":"models/lwf.py","file_url":"https://github.com/loribonna/cssl/blob/HEAD/models/lwf.py","link_basis":"plan_row","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":"bc5d184387cac930"}},{"code_sha256_prefix":"17f99e057c3caa2b","entry":"ResNet18","repo":"loribonna/cssl","repo_kind":"official","path":"backbone/ResNet18.py","file_url":"https://github.com/loribonna/cssl/blob/HEAD/backbone/ResNet18.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":"17f99e057c3caa2b"}},{"code_sha256_prefix":"4c2989ace7c5c0da","entry":"conv3x3","repo":"loribonna/cssl","repo_kind":"official","path":"backbone/ResNet18.py","file_url":"https://github.com/loribonna/cssl/blob/HEAD/backbone/ResNet18.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":"4c2989ace7c5c0da"}},{"code_sha256_prefix":"d44ae5af88b0c095","entry":"normalize","repo":"loribonna/cssl","repo_kind":"official","path":"models/ccic.py","file_url":"https://github.com/loribonna/cssl/blob/HEAD/models/ccic.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":"d44ae5af88b0c095"}},{"code_sha256_prefix":"47c2a6279c2181ca","entry":"random_crop","repo":"loribonna/cssl","repo_kind":"official","path":"models/ccic.py","file_url":"https://github.com/loribonna/cssl/blob/HEAD/models/ccic.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":"47c2a6279c2181ca"}},{"code_sha256_prefix":"9c7d99ad8fa869d9","entry":"random_flip","repo":"loribonna/cssl","repo_kind":"official","path":"models/ccic.py","file_url":"https://github.com/loribonna/cssl/blob/HEAD/models/ccic.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":"9c7d99ad8fa869d9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}