论文阅读笔记《Meta R-CNN : Towards General Solver for Instance-level Low-shot Learning》
核心思想 本文基于Faster/Mask R-CNN提出一种小样本目标检测/分割网络（Meta R-CNN）。文章保留了Faster/Mask R-CNN两阶段式的结构，整体网络结构如下图所示 首先，查询集图片经过特征提取网络和RPN网络（与Faster/Mask R-CNN中相同）得到感兴趣区域的特征图 z i z_i zi。然后支持集图像和对应的真实标签图经过预测器重建模网络（Pre
相关文章
- 1. 论文阅读笔记 Meta-Learning for Batch Mode Active Learning
- 2. 论文阅读笔记《Meta-Learning of Neural Architectures for Few-Shot Learning》
- 3. 论文阅读笔记《Task-Agnostic Meta-Learning for Few-shot Learning》
- 4. 论文阅读笔记《Meta-SGD: Learning to Learn Quickly for Few-Shot Learning》
- 5. RCNN论文阅读笔记
- 6. 论文阅读笔记《Image Deformation Meta-Networks for One-Shot Learning》
- 7. 论文阅读笔记 [ICLR 2018] Meta-Learning For Semi-Supervised Few-Shot
- 8. 论文阅读笔记《Meta-learning for semi-supervised few-shot classification》
- 9. 论文阅读笔记《Deep Meta-Learning: Learning to Learn in the Concept Space》
- 10. 2018-04-Towards High Performance Video Object Detection for Mobiles-论文阅读笔记
- 更多相关文章...
- • RSS 阅读器 - RSS 教程
- • PHP 实例 - AJAX RSS 阅读器 - PHP教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • JDK13 GA发布：5大特性解读
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 论文阅读笔记 Meta-Learning for Batch Mode Active Learning
- 2. 论文阅读笔记《Meta-Learning of Neural Architectures for Few-Shot Learning》
- 3. 论文阅读笔记《Task-Agnostic Meta-Learning for Few-shot Learning》
- 4. 论文阅读笔记《Meta-SGD: Learning to Learn Quickly for Few-Shot Learning》
- 5. RCNN论文阅读笔记
- 6. 论文阅读笔记《Image Deformation Meta-Networks for One-Shot Learning》
- 7. 论文阅读笔记 [ICLR 2018] Meta-Learning For Semi-Supervised Few-Shot
- 8. 论文阅读笔记《Meta-learning for semi-supervised few-shot classification》
- 9. 论文阅读笔记《Deep Meta-Learning: Learning to Learn in the Concept Space》
- 10. 2018-04-Towards High Performance Video Object Detection for Mobiles-论文阅读笔记