探索视觉先验知识如何提升数据稀缺下的模型性能
Data-Efficient Challenges in Visual Inductive Priors: A Retrospective
- 通过四场数据受限挑战赛，测试从零训练模型的效率
- 混合Transformer与CNN的大型模型集成+强数据增强表现最佳
- 适合关注小样本学习与模型先验设计的研究者
深度学习通常需要大量数据才能取得良好性能，在数据稀缺场景下表现下降。本文通过组织“VIPriors：面向数据高效深度学习的视觉归纳先验”系列研讨会，举办四届数据受限挑战赛，聚焦在有限数据下训练计算机视觉模型的问题。参赛者需从头训练模型，禁止使用迁移学习。目标是推动融合先验知识的新方法发展，以提升深度学习的数据效率。成功方案普遍采用混合Transformer与CNN的大规模模型集成，结合高强度数据增强；部分优秀方案还引入了基于先验知识的新方法，显著提升了小样本训练效果。
原文摘要 · Abstract (English)
Deep Learning requires large amounts of data to train models that work well. In data-deficient settings, performance can be degraded. We investigate which Deep Learning methods benefit training models in a data-deficient setting, by organizing the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop series, featuring four editions of data-impaired challenges. These challenges address the problem of training deep learning models for computer vision tasks with limited data. Participants are limited to training models from scratch using a low number of training samples and are not allowed to use any form of transfer learning. We aim to stimulate the development of novel approaches that incorporate prior knowledge to improve the data efficiency of deep learning models. Successful challenge entries make use of large model ensembles that mix Transformers and CNNs, as well as heavy data augmentation. Novel prior knowledge-based methods contribute to success in some entries.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。