Pirinen-CVPR-2018
Pirinen, Aleksis, and Cristian Sminchisescu. "Deep reinforcement learning of region proposal networks for object detection." proceedings of the IEEE conference on computer v...
Pirinen, Aleksis, and Cristian Sminchisescu. "Deep reinforcement learning of region proposal networks for object detection." proceedings of the IEEE conference on computer v...
Mathe, Stefan, Aleksis Pirinen, and Cristian Sminchisescu. "Reinforcement learning for visual object detection." Proceedings of the IEEE conference on computer vision and patter...
整体架构:与Janus同。
改进点:
10%考勤+90%大作业
affect(情感)范围广:包括emotion(情绪)、mood/state(心境/状态)
我勒个豆,我写了好几天,令人感叹的效率()
感觉似乎V3的内容会多一点,然后R1和R1-Zero会比较偏向于阐述(?)
或者说是因为细节的东西没给出来,所以全是大段地阐述文字,基本框架组件和v3应该一致.
具体到奖励函数的设计,\(r_i\)等等,就没有详细的解释了.
[TOC]
- 写出具体任务:输入输出,对问题要比较明确。
- 面临挑战
- 当前领域的经典方法,和最新方法benchmark
- 给出自己的技术路线