首个融合少样本学习与领域自适应的统一框架，支持多任务部署。
LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning
- 模块化设计，可灵活组合少样本与领域自适应方法。
- 支持动态构建增量式n-shot任务，兼容传统多样本任务。
- 集成多种自监督预训练配置，适配当前主流少样本学习研究。
少样本学习与领域自适应在计算机视觉中均取得了显著进展，现有算法和数据集日益丰富。然而，尚未有统一框架同时整合这两项技术。本文提出首个融合少样本学习与领域自适应的统一框架，涵盖图像分类、目标检测和视频分类三类任务。该框架高度模块化，可根据需要选择是否引入领域自适应；其核心特性是支持实时配置增量式n-shot任务，也可扩展至传统多样本任务。鉴于当前少样本学习对自监督学习（SSL）的高度依赖，本框架还支持多种SSL预训练配置。为验证框架性能，我们在多个算法与数据集上进行了广泛测试，涵盖不同任务与问题设置。代码已开源，地址：https://gitlab.kitware.com/darpa_learn/learn。
原文摘要 · Abstract (English)
Both few-shot learning and domain adaptation sub-fields in Computer Vision have seen significant recent progress in terms of the availability of state-of-the-art algorithms and datasets. Frameworks have been developed for each sub-field; however, building a common system or framework that combines both is something that has not been explored. As part of our research, we present the first unified framework that combines domain adaptation for the few-shot learning setting across 3 different tasks - image classification, object detection and video classification. Our framework is highly modular with the capability to support few-shot learning with/without the inclusion of domain adaptation depending on the algorithm. Furthermore, the most important configurable feature of our framework is the on-the-fly setup for incremental $n$-shot tasks with the optional capability to configure the system to scale to a traditional many-shot task. With more focus on Self-Supervised Learning (SSL) for current few-shot learning approaches, our system also supports multiple SSL pre-training configurations. To test our framework's capabilities, we provide benchmarks on a wide range of algorithms and datasets across different task and problem settings. The code is open source has been made publicly available here: https://gitlab.kitware.com/darpa_learn/learn
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。