{"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/i-3net-implicit-instance-invariant-network","title":"I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors","arxiv_id":"2103.13757","date":"2021-03-25","proceeding":"CVPR 2021 1","authors":["Chaoqi Chen","Zebiao Zheng","Yue Huang","Xinghao Ding","Yizhou Yu"],"abstract":"Recent works on two-stage cross-domain detection have widely explored the local feature patterns to achieve more accurate adaptation results. These methods heavily rely on the region proposal mechanisms and ROI-based instance-level features to design fine-grained feature alignment modules with respect to the foreground objects. However, for one-stage detectors, it is hard or even impossible to obtain explicit instance-level features in the detection pipelines. Motivated by this, we propose an Implicit Instance-Invariant Network (I3Net), which is tailored for adapting one-stage detectors and implicitly learns instance-invariant features via exploiting the natural characteristics of deep features in different layers. Specifically, we facilitate the adaptation from three aspects: (1) Dynamic and Class-Balanced Reweighting (DCBR) strategy, which considers the coexistence of intra-domain and intra-class variations to assign larger weights to those sample-scarce categories and easy-to-adapt samples; (2) Category-aware Object Pattern Matching (COPM) module, which boosts the cross-domain foreground objects matching guided by the categorical information and suppresses the uninformative background features; (3) Regularized Joint Category Alignment (RJCA) module, which jointly enforces the category alignment at different domain-specific layers with a consistency regularization. Experiments reveal that I3Net exceeds the state-of-the-art performance on benchmark datasets.","url_abs":"https://arxiv.org/abs/2103.13757v2","url_pdf":"https://arxiv.org/pdf/2103.13757v2.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":"i-3net-implicit-instance-invariant-network","repo_url":"https://github.com/czzbb/I3Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"region-proposal","task_name":"Region Proposal"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.13757","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}