- 博客(5)
- 资源 (1)
- 收藏
- 关注
RSS订阅原创 CVPR2020 Harmonizing Transferability and Discriminability for Adapting Object Detector
Harmonizing Transferability and Discriminability for Adapting Object Detectorcode:https://github.com/chaoqichen/HTCNAbstract论文中设计了三个模块，用于源域和目标域之间的对齐，同时能够使得检测器能够对源域特征和目标域特征具有一定的辨别能力。(1) Importance Weighted Adversarial Training with input Interpolatio
2021-02-22 16:41:37
908
原创 CVPR2019 Strong-Weak Distribution Alignment for Adaptive Object Detection
Strong-Weak Distribution Alignment for Adaptive Object DetectionCode: https://github.com/VisionLearningGroup/DA_DetectionIntroduction对于目标检测任务而言，简单地对源域和目标域之间整张图的分布进行对齐往往并不是很有效，因为不同地图像包含有多种目标。然而对局部特征如纹理、颜色等进行对齐，这样不会改变类别层次的语义，往往很有效。传统的方法是对利用对抗的方法来利用两个域之间的
2021-01-12 15:21:15
780
原创 AAAI2020 iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
iFAN: Image-Instance Full Alignment Networks for Adaptive Object DetectionMotivationWe propose Image-Instance Full Alignment Networks (iFAN) to tackle this problem by precisely aligning feature distributions on both image and instance levels: 1) Image-l
2021-01-12 14:49:48
404
原创 Object Detection && Domain Adaption
CVPR2018 & CVPR2019【目标检测+域适应】CVPR18 CVPR19总结
2020-09-17 09:43:41
265
原创 贪心算法——坐板凳问题
将板凳0与小朋友1任意排列，每个小朋友可以坐离其距离范围为k的任意一个板凳，每个人只能坐一个板凳，有多少个小朋友能坐到板凳？如下输入输出:input '101100',k=2output :3贪心算法：查找当前小朋友前后k个位置的板凳，存在空闲板凳占用即可。#include<iostream>#include<string>#include<a...
2019-11-30 11:09:14
523
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人