深度学习:论文self-trainsfer learning for weakly supervised lesion localization
2018-11-25 19:46
543 查看
self-training learning: 自我训练学习
weakly supervised :弱监督学习
主要关注三种弱监督类型:
- 第一种是不完全监督,即只有训练数据集的一个(通常很小的)子集有标签,其它数据则没有标签。
- 第二种是不确切监督,即只有粗粒度的标签。又以图像分类任务为例。我们希望图片中的每个物体都被标注;然而我们只有图片级的标签而没有物体级的标签。
- 第三种是不准确监督,即给定的标签并不总是真值。出现这种情况的原因有,标注者粗心或疲倦,或者一些图像本身就难以分类。
已知数据和其一一对应的弱标签,训练一个智能算法,将输入数据映射到一组更强的标签的过程。标签的强弱指的是标签蕴含的信息量的多少,比如相对于分割的标签来说,分类的标签就是弱标签,如果我们知道一幅图,告诉你图上有一只猪,然后需要你把猪在哪里,猪和背景的分界在哪里找出来,那么这就是一个已知弱标签,去学习强标签的弱监督学习问题
相关文章推荐
- Deep Self-Taught Learning for Weakly Supervised Object Localization
- 目标定位--Deep Self-Taught Learning for Weakly Supervised Object Localization
- Two-Phase Learning for Weakly Supervised Object Localization
- 论文笔记《IS object localization for free? Weakly-supervised learning with convolutional neural network》
- 《Deep Self-Taught Learning for Weakly Supervised Object Localization》
- 论文阅读笔记 | (IJCAI 2018 Oral) Collaborative Learning for Weakly Supervised Object Detection
- Learning Deep Features for Discriminative Localization论文笔记以及Caffe实现
- 论文阅读-《Learning Deep Features for Discriminative Localization》
- [EMNLP2017]Deep Residual Learning for Weakly-Supervised Relation Extraction
- 论文笔记-深度估计(4) Semi-Supervised Deep Learning for Monocular Depth Map Prediction
- 论文阅读:《LIP: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing》
- 论文研读--Weakly Supervised Object Localization with Progressive Domain Adaptation
- Self-Supervised Learning for Stereo Matching with Self-Improving Ability
- 论文阅读Soft Proposal Networks for weekly-supervised object localization
- 行人属性“Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Loca”
- 论文阅读-《Learning Deep Features for Discriminative Localization》
- 论文笔记 | Learning Deep Features for Discriminative Localization
- 论文阅读-《Learning Deep Features for Discriminative Localization》
- 论文笔记--STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
- 论文笔记 | 基于深度学习的乳腺转移瘤识别(Deep Learning for Identifying Metastatic Breast Cancer)