迁移学习/领域适应/领域概括/多任务学习等。论文、代码、数据集、应用程序、教程。-迁移学习
few-shot 开源项目推荐(207 个)
few-shot 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 207 个仓库[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction
A PyTorch Library for Meta-learning Research
按子领域分类的扩散模型论文集
定制扩散:文本到图像扩散的多概念定制(CVPR 2023)
FSL-Mate: A collection of resources for few-shot learning (FSL).
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
A unified multi-task time series model.
Meta-Learning with Differentiable Convex Optimization (CVPR 2019 Oral)
Tools for generating mini-ImageNet dataset and processing batches
The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"
Zero and Few 拍摄了命名实体及关系识别
BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
这是《有限数据滚轴承故障诊断与少数测绘学习》论文的相应存储库
A transfer learning fault diagnosis repository covering popular algorithms
FewX is an open-source toolbox on top of Detectron2 for data-limited instance-level recognition tasks.
PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation (TPAMI).
[CVPR 2023 Workshop] VAND Challenge: 1st Place on Zero-shot AD and 4th Place on Few-shot AD
Pytorch implementation of the paper "Optimization as a Model for Few-Shot Learning"
[NeurIPS 2021]Deceive D:数据有限的 GAN 自适应伪增强
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/few-shot。
- 该话题在 GitHub 上共有 207 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 3.4 万 Star,覆盖 2 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。