{"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/unified-probabilistic-deep-continual-learning","title":"Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition","arxiv_id":"1905.12019","date":"2019-05-28","proceeding":null,"authors":["Martin Mundt","Iuliia Pliushch","Sagnik Majumder","Yongwon Hong","Visvanathan Ramesh"],"abstract":"Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts, the corresponding literature appears to nonetheless focus primarily on alleviating catastrophic interference with learned representations. In this work, we introduce a probabilistic approach that connects these perspectives based on variational inference in a single deep autoencoder model. Specifically, we propose to bound the approximate posterior by fitting regions of high density on the basis of correctly classified data points. These bounds are shown to serve a dual purpose: unseen unknown out-of-distribution data can be distinguished from already trained known tasks towards robust application. Simultaneously, to retain already acquired knowledge, a generative replay process can be narrowed to strictly in-distribution samples, in order to significantly alleviate catastrophic interference.","url_abs":"https://arxiv.org/abs/1905.12019v5","url_pdf":"https://arxiv.org/pdf/1905.12019v5.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":"unified-probabilistic-deep-continual-learning","repo_url":"https://github.com/MrtnMndt/OCDVAE_ContinualLearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unified-probabilistic-deep-continual-learning","repo_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unified-probabilistic-deep-continual-learning","repo_url":"https://github.com/TimmHess/OCDVAEContinualLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"open-set-learning","task_name":"Open Set Learning"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.12019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12019"}},"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/TimmHess/OCDVAEContinualLearning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MrtnMndt/OCDVAEContinualLearning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MrtnMndt/OCDVAE_ContinualLearning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":13},"by_repo_kind":{"official":{"samples":12,"ran":0,"repositories":1},"listed":{"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":0,"samples":[{"code_sha256_prefix":"35a868da9fed37c9","entry":"KLD","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/Training/loss_functions.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Training/loss_functions.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":"35a868da9fed37c9"}},{"code_sha256_prefix":"acecd7a6217e354d","entry":"augment_data","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/Training/augmentation.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Training/augmentation.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":"acecd7a6217e354d"}},{"code_sha256_prefix":"4333c3e5ee86bb81","entry":"augment_flip","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/Training/augmentation.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Training/augmentation.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":"4333c3e5ee86bb81"}},{"code_sha256_prefix":"77b460b279b0da2d","entry":"augment_random_translate","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/Training/augmentation.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Training/augmentation.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":"77b460b279b0da2d"}},{"code_sha256_prefix":"4bf4bed0805b9389","entry":"calc_distances_to_means","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/OpenSet/meta_recognition.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/OpenSet/meta_recognition.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":"4bf4bed0805b9389"}},{"code_sha256_prefix":"b3576c10e8d51fce","entry":"encoder_loss_with_fake","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/Training/loss_functions.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Training/loss_functions.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":"b3576c10e8d51fce"}},{"code_sha256_prefix":"5bb73bb78d01fb53","entry":"eval_dataset","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/Training/evaluate.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Training/evaluate.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":"5bb73bb78d01fb53"}},{"code_sha256_prefix":"ff4c1bd619f2a04b","entry":"eval_openset_dataset","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/Training/evaluate.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Training/evaluate.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":"ff4c1bd619f2a04b"}},{"code_sha256_prefix":"8b8425aa050b8c28","entry":"get_feat_size","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/Models/architectures.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Models/architectures.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":"8b8425aa050b8c28"}},{"code_sha256_prefix":"f28bb4760db0af78","entry":"get_latent_embedding","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/Training/evaluate.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Training/evaluate.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":"f28bb4760db0af78"}},{"code_sha256_prefix":"9a2c9f801548b8b5","entry":"get_means","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/OpenSet/meta_recognition.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/OpenSet/meta_recognition.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":"9a2c9f801548b8b5"}},{"code_sha256_prefix":"13389065de3e98b6","entry":"joint_loss_function","repo":"MrtnMndt/OCDVAEContinualLearning","repo_kind":"official","path":"lib/Training/loss_functions.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Training/loss_functions.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":"13389065de3e98b6"}},{"code_sha256_prefix":"41cc1bfa6d07666f","entry":"surrogate_loss","repo":"TimmHess/OCDVAEContinualLearning","repo_kind":"listed","path":"lib/Models/si.py","file_url":"https://github.com/TimmHess/OCDVAEContinualLearning/blob/HEAD/lib/Models/si.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":"41cc1bfa6d07666f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}