{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/small-task-incremental-learning","title":"PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning","arxiv_id":"2004.13513","date":"2020-04-28","proceeding":"ECCV 2020 8","authors":["Arthur Douillard","Matthieu Cord","Charles Ollion","Thomas Robert","Eduardo Valle"],"abstract":"Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learning. In this work, we propose PODNet, a model inspired by representation learning. By carefully balancing the compromise between remembering the old classes and learning new ones, PODNet fights catastrophic forgetting, even over very long runs of small incremental tasks --a setting so far unexplored by current works. PODNet innovates on existing art with an efficient spatial-based distillation-loss applied throughout the model and a representation comprising multiple proxy vectors for each class. We validate those innovations thoroughly, comparing PODNet with three state-of-the-art models on three datasets: CIFAR100, ImageNet100, and ImageNet1000. Our results showcase a significant advantage of PODNet over existing art, with accuracy gains of 12.10, 6.51, and 2.85 percentage points, respectively. Code is available at https://github.com/arthurdouillard/incremental_learning.pytorch","url_abs":"https://arxiv.org/abs/2004.13513v3","url_pdf":"https://arxiv.org/pdf/2004.13513v3.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":"small-task-incremental-learning","repo_url":"https://github.com/arthurdouillard/incremental_learning.pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"small-task-incremental-learning","repo_url":"https://github.com/g-u-n/pycil","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/incremental-learning-on-cifar-100-50-classes-2","task":"Incremental Learning","dataset":"CIFAR-100 - 50 classes + 10 steps of 5 classes","model":"PODNet (CNN)","rank_in_archive_order":9,"of":13,"metrics":{"Average Incremental Accuracy":"63.19"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-cifar-100-50-classes-1","task":"Incremental Learning","dataset":"CIFAR-100 - 50 classes + 25 steps of 2 classes","model":"PODNet","rank_in_archive_order":4,"of":5,"metrics":{"Average Incremental Accuracy":"60.72"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-cifar-100-50-classes-3","task":"Incremental Learning","dataset":"CIFAR-100 - 50 classes + 5 steps of 10 classes","model":"PODNet (CNN)","rank_in_archive_order":9,"of":15,"metrics":{"Average Incremental Accuracy":"64.83"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-cifar-100-50-classes","task":"Incremental Learning","dataset":"CIFAR-100 - 50 classes + 50 steps of 1 class","model":"PODNet","rank_in_archive_order":1,"of":2,"metrics":{"Average Incremental Accuracy":"57.98"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-cifar-100-b0-5steps","task":"Incremental Learning","dataset":"CIFAR-100-B0(5steps of 20 classes)","model":"PODNet","rank_in_archive_order":9,"of":10,"metrics":{"Average Incremental Accuracy":"66.70"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-imagenet-500-classes-2","task":"Incremental Learning","dataset":"ImageNet - 500 classes + 10 steps of 50 classes","model":"PODNet","rank_in_archive_order":2,"of":4,"metrics":{"Average Incremental Accuracy":"64.13"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-imagenet-500-classes-1","task":"Incremental Learning","dataset":"ImageNet - 500 classes + 5 steps of 100 classes","model":"PODNet","rank_in_archive_order":3,"of":4,"metrics":{"Average Incremental Accuracy":"66.95"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-imagenet-100-50-2","task":"Incremental Learning","dataset":"ImageNet-100 - 50 classes + 10 steps of 5 classes","model":"PODNet","rank_in_archive_order":5,"of":5,"metrics":{"Average Incremental Accuracy":"73.14"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-imagenet-100-50-1","task":"Incremental Learning","dataset":"ImageNet-100 - 50 classes + 25 steps of 2 classes","model":"PODNet","rank_in_archive_order":3,"of":3,"metrics":{"Average Incremental Accuracy":"67.28"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-imagenet-100-50-3","task":"Incremental Learning","dataset":"ImageNet-100 - 50 classes + 5 steps of 10 classes","model":"PODNet","rank_in_archive_order":4,"of":5,"metrics":{"Average Incremental Accuracy":"75.82"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-imagenet-100-50","task":"Incremental Learning","dataset":"ImageNet-100 - 50 classes + 50 steps of 1 class","model":"PODNet","rank_in_archive_order":1,"of":2,"metrics":{"Average Incremental Accuracy":"62.08"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"arthurdouillard/incremental_learning.pytorch","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"g-u-n/pycil","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2301.05792"],"harvested_for_calls":[{"arxiv_id":"2301.05792","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.05792"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.05792\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9d2793cb0e18de7f3c3048902cce2faf9ff20f204953beb5df05d07e4f945774","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}