《学习笔记》
文章目录
- Generals
- Process
- 数据
- Trian
- Inner loop for MAML ProtoNet
- AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration
- [6]Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
- [18]Simarpn++
Generals
supervised vs few-shot learning
- inference的data是test data
- supervised train的data有inference碰到的categories
- inference的data是query data
- 但是few-shot train的data里不一定有inference碰到的categories
- k-way:support set(training data) 有 k 个categories
- n-shot: every category has n samples
- training set: 猫的training data有10张,狗的training data也有10张,则这种情况,k = 2, n = 10
- 通常来说,随着categories的增多,检测的准确率会下降。因为种类的增多越来越会像“大海捞针”,检测击中目标的难度会增加
- 重点在于similarities的计算。从一个大的数据集学习到一个similarity function
siamese Net
- 用了正负样本的set
- 用了binary loss