经典的跨域算法通常会对源域进行处理:1. style transfer (已知目标域的风格,只使用了目标域先验); 2. Domian Randomization(不知目标域风格,增强模型跨域表达能力,没有使用目标先验)。这些转换方式不是最优的,因此作者提出了基于任务和目标风格的自动搜索转换器。具体做法如下所示:每获得一个转换器,就把转换器得到...
Cross-Domain Multi-Task Learning for Object Detection and Saliency Estimation Error-aware density isomorphism reconstruction for unsupervised cross-domain crowd counting Domain structure-based transfer learning for cross-domain word representation Cross-Domain Similarity Learning for Face Recognition in Unseen D...
内容提示: Leveraging Self-Supervision for Cross-Domain Crowd CountingWeizhe Liu Nikita Durasov Pascal FuaComputer Vision Laboratory,´Ecole Polytechnique Fédérale de Lausanne (EPFL){weizhe.liu, nikita.durasov, pascal.fua}@epfl.chAbstractState-of-the-art methods for counting people in crowdedscenes...
Bi-level Alignment for Cross-Domain Crowd Counting Shenjian Gong1, Shanshan Zhang1,*, Jian Yang1, Dengxin Dai2, and Bernt Schiele2 1PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Vide...
A head-aware density adaptive network (HADAN) is proposed for cross-domain crowd counting to solve these problems. In style transform part, the ground-truth of the source domain dataset is firstly used to generate the mask of the head area and background area, and then a head-aware cycle...
README.md add implementation May 4, 2022 model.py add implementation May 4, 2022 README This repository is a PyTorch implementation for the paperLeveraging Self-Supervision for Cross-Domain Crowd Counting, which is accepted asoralpresentation at CVPR 2022. If you use this code in your research...
Due to the hidden nodes, the conditional probability of cannot be drawn simply by counting the occurrence of each condition. An EM algorithm was proposed to learn the parameters in an unsupervised manner. Example 14: Yuan et al. [74][76] infer the functional re- gions in a city using ...
CNN-based crowd-counting algorithms usually consist of feature extraction, density estimation, and count regression. To improve the domain adaptation in feature extraction, we propose an adaptive domain-invariant feature extracting module. Meanwhile, after taking inspiration from recent innovative meta-...