Instance Segmentation Model Retrieval using Performance Prediction and Learning to Rank

• 資料種別: 記事
• タイトル: Instance Segmentation Model Retrieval using Performance Prediction and Learning to Rank
• 著者標目: Pham Huu-Long; Kubouchi Masataka; Nishimoto Takuma; Yamamoto Takehiro; Ohshima Hiroaki
• 出版年月日等: 2025
• 出版年（W3CDTF）: 2025
• タイトル（掲載誌）: Journal of Information Processing
• 巻号年月日等（掲載誌）: 33 0
• 掲載巻: 33
• 掲載号: 0
• 掲載ページ: 866-879
• 掲載年月日（W3CDTF）: 2025
• 出版事項（掲載誌）: Information Processing Society of Japan
• 本文の言語コード: en
• 件名標目: machine learning model retrieval; learning to rank; instance segmentation
• 対象利用者: 一般
• DOI: 10.2197/ipsjjip.33.866; https://doi.org/10.2197/ipsjjip.33.866
• 関連情報（URI）: https://www.jstage.jst.go.jp/article/ipsjjip/33/0/33_866/_pdf
• 参照: Learning to rank; https://cir.nii.ac.jp/crid/1360011145326719104; Exploring Simple Siamese Representation Learning; https://cir.nii.ac.jp/crid/1360016870036486912; Ranking Models in Unlabeled New Environments; https://cir.nii.ac.jp/crid/1360025029384880640; Listwise approach to learning to rank; https://cir.nii.ac.jp/crid/1360292620564833024; Segment Anything; https://cir.nii.ac.jp/crid/1360299770325395584; Pairwise Learning to Rank by Neural Networks Revisited: Reconstruction, Theoretical Analysis and Practical Performance; https://cir.nii.ac.jp/crid/1360302870441950464; Efficient Transferability Assessment for Selection of Pre-trained Detectors; https://cir.nii.ac.jp/crid/1360306504331484672; Transferability Metrics for Selecting Source Model Ensembles; https://cir.nii.ac.jp/crid/1360306504348147968; TSPRank: Bridging Pairwise and Listwise Methods with a Bilinear Travelling Salesman Model; https://cir.nii.ac.jp/crid/1360306508631882752; Image-Generation AI Model Retrieval by Contrastive Learning-Based Style Distance Calculation; https://cir.nii.ac.jp/crid/1360306509098541056; Make Large Language Model a Better Ranker; https://cir.nii.ac.jp/crid/1360306509100596352; Learning to rank using gradient descent; https://cir.nii.ac.jp/crid/1360574096444254080; Learning to Rank with Nonsmooth Cost Functions; https://cir.nii.ac.jp/crid/1360861293421426560; Pranking with Ranking; https://cir.nii.ac.jp/crid/1360862718498344832; Inference-Based No-Learning Approach on Pre-Trained BERT Model Retrieval; https://cir.nii.ac.jp/crid/1360865815501278848; LiPO: Listwise Preference Optimization through Learning-to-Rank; https://cir.nii.ac.jp/crid/1360869454548346368; Mask R-CNN; https://cir.nii.ac.jp/crid/1361137044369606016; Microsoft COCO: Common Objects in Context; https://cir.nii.ac.jp/crid/1361137044941077760; YOLACT: Real-Time Instance Segmentation; https://cir.nii.ac.jp/crid/1361981470736742912
• 連携機関・データベース: 国立情報学研究所 : CiNii Research; https://cir.nii.ac.jp/
• 提供元機関・データベース: Japan Link Center; https://japanlinkcenter.org/top; Crossref; https://www.crossref.org

• 要約等: <p>In this research, we propose a method to efficiently retrieve instance segmentation models that perform well on a specific image. With the advancem...