{"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/mila-memory-based-instance-level-adaptation-1","title":"MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection","arxiv_id":"2309.01086","date":"2023-09-03","proceeding":null,"authors":["Onkar Krishna","Hiroki Ohashi","Saptarshi Sinha"],"abstract":"Cross-domain object detection is challenging, and it involves aligning labeled source and unlabeled target domains. Previous approaches have used adversarial training to align features at both image-level and instance-level. At the instance level, finding a suitable source sample that aligns with a target sample is crucial. A source sample is considered suitable if it differs from the target sample only in domain, without differences in unimportant characteristics such as orientation and color, which can hinder the model's focus on aligning the domain difference. However, existing instance-level feature alignment methods struggle to find suitable source instances because their search scope is limited to mini-batches. Mini-batches are often so small in size that they do not always contain suitable source instances. The insufficient diversity of mini-batches becomes problematic particularly when the target instances have high intra-class variance. To address this issue, we propose a memory-based instance-level domain adaptation framework. Our method aligns a target instance with the most similar source instance of the same category retrieved from a memory storage. Specifically, we introduce a memory module that dynamically stores the pooled features of all labeled source instances, categorized by their labels. Additionally, we introduce a simple yet effective memory retrieval module that retrieves a set of matching memory slots for target instances. Our experiments on various domain shift scenarios demonstrate that our approach outperforms existing non-memory-based methods significantly.","url_abs":"https://arxiv.org/abs/2309.01086v1","url_pdf":"https://arxiv.org/pdf/2309.01086v1.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":"mila-memory-based-instance-level-adaptation-1","repo_url":"https://github.com/hitachi-rd-cv/MILA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-comic2k","task":"Domain Adaptation","dataset":"Comic2k","model":"MILA","rank_in_archive_order":2,"of":2,"metrics":{" mAP":"44.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-foggy-cityscapes","task":"Domain Adaptation","dataset":"Foggy Cityscapes","model":"MILA","rank_in_archive_order":1,"of":1,"metrics":{"mAP":"50.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-sim10k","task":"Domain Adaptation","dataset":"Sim10k","model":"MILA","rank_in_archive_order":1,"of":1,"metrics":{"mAP":"57.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-pascal-voc-to-clipart1k","task":"Object Detection","dataset":"Pascal VOC to Clipart1K","model":"MILA","rank_in_archive_order":2,"of":3,"metrics":{"mAP":"49.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-sim10k-to-3","task":"Unsupervised Domain Adaptation","dataset":"SIM10K to Cityscapes","model":"MILA","rank_in_archive_order":10,"of":13,"metrics":{"mAP@0.5":"57.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.01086","atlas_url":"https://app.syntology.ai/?focus=2309.01086","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":"2309.01086"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2309.01086\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2309.01086"},"call":"get_concepts_for_paper(arxiv_id=\"2309.01086\")"}],"by_repo":[{"repo":"hitachi-rd-cv/MILA","kind":"listed","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":"72f20829c57501d598b26eb22efdda44d2efbb6dabccf9756a9d973ee3fd89c1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}