{"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/piggyback-adapting-a-single-network-to","title":"Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights","arxiv_id":"1801.06519","date":"2018-01-19","proceeding":"ECCV 2018 9","authors":["Arun Mallya","Dillon Davis","Svetlana Lazebnik"],"abstract":"This work presents a method for adapting a single, fixed deep neural network\nto multiple tasks without affecting performance on already learned tasks. By\nbuilding upon ideas from network quantization and pruning, we learn binary\nmasks that piggyback on an existing network, or are applied to unmodified\nweights of that network to provide good performance on a new task. These masks\nare learned in an end-to-end differentiable fashion, and incur a low overhead\nof 1 bit per network parameter, per task. Even though the underlying network is\nfixed, the ability to mask individual weights allows for the learning of a\nlarge number of filters. We show performance comparable to dedicated fine-tuned\nnetworks for a variety of classification tasks, including those with large\ndomain shifts from the initial task (ImageNet), and a variety of network\narchitectures. Unlike prior work, we do not suffer from catastrophic forgetting\nor competition between tasks, and our performance is agnostic to task ordering.\nCode available at https://github.com/arunmallya/piggyback.","url_abs":"http://arxiv.org/abs/1801.06519v2","url_pdf":"http://arxiv.org/pdf/1801.06519v2.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":"piggyback-adapting-a-single-network-to","repo_url":"https://github.com/arunmallya/piggyback","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/continual-learning-on-cubs-fine-grained-6","task":"Continual Learning","dataset":"CUBS (Fine-grained 6 Tasks)","model":"Piggyback","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"80.5"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-flowers-fine-grained-6","task":"Continual Learning","dataset":"Flowers (Fine-grained 6 Tasks)","model":"Piggyback","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"94.77"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-imagenet-fine-grained-6","task":"Continual Learning","dataset":"ImageNet (Fine-grained 6 Tasks)","model":"Piggyback","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"76.16"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-sketch-fine-grained-6","task":"Continual Learning","dataset":"Sketch (Fine-grained 6 Tasks)","model":"Piggyback","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"79.91"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-stanford-cars-fine","task":"Continual Learning","dataset":"Stanford Cars (Fine-grained 6 Tasks)","model":"Piggyback","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"89.62"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-wikiart-fine-grained-6","task":"Continual Learning","dataset":"Wikiart (Fine-grained 6 Tasks)","model":"Piggyback","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy":"71.33"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-visual-domain-decathlon","task":"Continual Learning","dataset":"visual domain decathlon (10 tasks)","model":"Piggyback","rank_in_archive_order":8,"of":14,"metrics":{"Avg. Accuracy":"76.60","decathlon discipline (Score)":"2838"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.06519","atlas_url":"https://app.syntology.ai/?focus=1801.06519","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1801.06519"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.06519\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.06519"},"call":"get_concepts_for_paper(arxiv_id=\"1801.06519\")"}],"by_repo":[{"repo":"arunmallya/piggyback","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"f41ff4e3d1cabceb0d7655083cedb6a1c7a5e074649ab0617cb347ada006531d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}