{"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/end-to-end-incremental-learning","title":"End-to-End Incremental Learning","arxiv_id":"1807.09536","date":"2018-07-25","proceeding":"ECCV 2018 9","authors":["Francisco M. Castro","Manuel J. Marín-Jiménez","Nicolás Guil","Cordelia Schmid","Karteek Alahari"],"abstract":"Although deep learning approaches have stood out in recent years due to their\nstate-of-the-art results, they continue to suffer from catastrophic forgetting,\na dramatic decrease in overall performance when training with new classes added\nincrementally. This is due to current neural network architectures requiring\nthe entire dataset, consisting of all the samples from the old as well as the\nnew classes, to update the model -a requirement that becomes easily\nunsustainable as the number of classes grows. We address this issue with our\napproach to learn deep neural networks incrementally, using new data and only a\nsmall exemplar set corresponding to samples from the old classes. This is based\non a loss composed of a distillation measure to retain the knowledge acquired\nfrom the old classes, and a cross-entropy loss to learn the new classes. Our\nincremental training is achieved while keeping the entire framework end-to-end,\ni.e., learning the data representation and the classifier jointly, unlike\nrecent methods with no such guarantees. We evaluate our method extensively on\nthe CIFAR-100 and ImageNet (ILSVRC 2012) image classification datasets, and\nshow state-of-the-art performance.","url_abs":"http://arxiv.org/abs/1807.09536v2","url_pdf":"http://arxiv.org/pdf/1807.09536v2.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":"end-to-end-incremental-learning","repo_url":"https://github.com/axelmukwena/biometricECG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"end-to-end-incremental-learning","repo_url":"https://github.com/fmcp/EndToEndIncrementalLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"end-to-end-incremental-learning","repo_url":"https://github.com/kibok90/iccv2019-inc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"end-to-end-incremental-learning","repo_url":"https://github.com/lalithjets/domain-adaptation-in-mtl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"end-to-end-incremental-learning","repo_url":"https://github.com/lalithjets/domain-generalization-for-surgical-scene-graph","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"end-to-end-incremental-learning","repo_url":"https://github.com/mmasana/FACIL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/incremental-learning-on-imagenet-10-steps","task":"Incremental Learning","dataset":"ImageNet - 10 steps","model":"E2E","rank_in_archive_order":10,"of":10,"metrics":{"# M Params":"11.68","Average Incremental Accuracy Top-5":"72.09","Final Accuracy Top-5":"52.29"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-imagenet100-10-steps","task":"Incremental Learning","dataset":"ImageNet100 - 10 steps","model":"E2E","rank_in_archive_order":11,"of":13,"metrics":{"# M Params":"11.22","Average Incremental Accuracy Top-5":"89.92","Final Accuracy Top-5":"80.29"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.09536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09536"}},"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/lalithjets/domain-adaptation-in-mtl","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/axelmukwena/biometricECG","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fmcp/EndToEndIncrementalLearning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kibok90/iccv2019-inc","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lalithjets/domain-generalization-for-surgical-scene-graph","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mmasana/FACIL","reach":null}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"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":"2acfc8cd3d4a7a41","entry":"block","repo":"axelmukwena/biometricECG","repo_kind":"listed","path":"cnn.py","file_url":"https://github.com/axelmukwena/biometricECG/blob/HEAD/cnn.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":"2acfc8cd3d4a7a41"}},{"code_sha256_prefix":"77a608bac7d684d4","entry":"create_pairs","repo":"axelmukwena/biometricECG","repo_kind":"listed","path":"snn.py","file_url":"https://github.com/axelmukwena/biometricECG/blob/HEAD/snn.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":"77a608bac7d684d4"}},{"code_sha256_prefix":"c2be16c19e6d55f9","entry":"filters","repo":"axelmukwena/biometricECG","repo_kind":"listed","path":"features.py","file_url":"https://github.com/axelmukwena/biometricECG/blob/HEAD/features.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":"c2be16c19e6d55f9"}},{"code_sha256_prefix":"4f1c51d7ade05617","entry":"filters","repo":"axelmukwena/biometricECG","repo_kind":"listed","path":"signals.py","file_url":"https://github.com/axelmukwena/biometricECG/blob/HEAD/signals.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":"4f1c51d7ade05617"}},{"code_sha256_prefix":"440f3333b608dcc5","entry":"load_data","repo":"axelmukwena/biometricECG","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/axelmukwena/biometricECG/blob/HEAD/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":"440f3333b608dcc5"}},{"code_sha256_prefix":"5cc2b83cb8447200","entry":"resamp","repo":"axelmukwena/biometricECG","repo_kind":"listed","path":"features.py","file_url":"https://github.com/axelmukwena/biometricECG/blob/HEAD/features.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":"5cc2b83cb8447200"}},{"code_sha256_prefix":"e88d07e0f6a17a4e","entry":"shuffle","repo":"axelmukwena/biometricECG","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/axelmukwena/biometricECG/blob/HEAD/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":"e88d07e0f6a17a4e"}},{"code_sha256_prefix":"07d3ea7e737fed96","entry":"splits","repo":"axelmukwena/biometricECG","repo_kind":"listed","path":"cnn.py","file_url":"https://github.com/axelmukwena/biometricECG/blob/HEAD/cnn.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":"07d3ea7e737fed96"}},{"code_sha256_prefix":"442205d6b4df4020","entry":"spp_layer","repo":"axelmukwena/biometricECG","repo_kind":"listed","path":"cnn.py","file_url":"https://github.com/axelmukwena/biometricECG/blob/HEAD/cnn.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":"442205d6b4df4020"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}