Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships
Rangel Daroya, Aaron Sun, Subhransu Maji
2024年份
1顶会引用
摘要
This suggests that low-dimensional box embeddings can effectively capture these task relationships and have the added advantage of being interpretable. We use the approach to visualize relationships among publicly available image classification datasets on popular dataset hosting platform called Hugging Face.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper1
问问它们各自怎么用它它引用的顶会 Paper20
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Open-vocabulary Object Detection via Vision and Language Knowledge DistillationXiuye Gu, Tsung-Yi Lin, Weicheng Kuo, Yin CuiICLR 2022 · 被引用 1,274 次
- Task2Vec: Task Embedding for Meta-LearningAlessandro Achille, Michael Lam, Rahul Tewari, Avinash Ravichandran 等ICCV 2019 · 被引用 359 次
- Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box EmbeddingsHongyu Ren, Weihua Hu, Jure LeskovecICLR 2020 · 被引用 355 次
- Efficiently Identifying Task Groupings for Multi-Task LearningChris Fifty, Ehsan Amid, Zhe Zhao, Tianhe Yu 等NeurIPS 2021 · 被引用 352 次
相关 Paper
- Low-dimensional Structure in the Space of Language Representations is Reflected in Brain ResponsesRichard J. Antonello, Javier S. Turek, Vy Ai Vo, Alexander HuthNeurIPS 2021 · 被引用 60 次
- Modeling Label Space Interactions in Multi-label Classification using Box EmbeddingsDhruvesh Patel, Pavitra Dangati, Jay-Yoon Lee, Michael Boratko 等ICLR 2022 · 被引用 28 次
- Hyperbolic Image EmbeddingsValentin Khrulkov, Leyla Mirvakhabova, Evgeniya Ustinova, Ivan V. Oseledets 等CVPR 2020
- A Single Vector Is Not Enough: Taxonomy Expansion via Box EmbeddingsSong Jiang, Qiyue Yao, Qifan Wang, Yizhou SunWWW 2023 · 被引用 20 次
- Modeling Fine-Grained Entity Types with Box EmbeddingsYasumasa Onoe, Michael Boratko, Andrew McCallum, Greg DurrettACL 2021
