今天有群友反馈弱监督目标检测论文少，收集了部分最新的 cap2det谷歌结合文字信息进行弱监督检测.pdf ICCV2019一篇 instance-aware弱监督目标检测CVPR2020 清华大学弱监督2019 商汤AAAI2020 中科院利用弱监督目标检测中的不稳定性 抛砖引玉，没有积分直接添加微信seer_ai发送 更多内容加微信免费获取

Weakly supervised object detection (WSOD) focuses on training object detector with only image-level annotations, and is challenging due to the gap between the supervision and the objective. 更多内容添加微信 seer_ai

Weaklysupervisedlearninghasemergedasacompelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2) detectors tend to f

机器学习分两大类，有监督学习(supervised learning)和无监督学习(unsupervised learning)。有监督学习又可分两类：分类（classification.）和回归（regression），分类的任务就是把一个样本划为某个已知类别，每个样本的类别信息在训练时需要给定，比如人脸识别、行为识别、目标检测等都属于分类。回归的任务则是预测一个数值，比如给定房屋市场的数据（面积，位置等样本信息）来预测房价走势。而无监督学习也可以成两类：聚类（clustering）和密度估计