Heatmap-based methods dominate in the field of human pose estimation by modelling the output distribution through likelihood heatmaps. In contrast, regression-based methods are more efficient but suffer from inferior performance. In this work, we explore maximum likelihood estimation (MLE) to develop an efficient and effective regression-based methods. From the perspective of MLE, adopting different regression losses is making different assumptions about the output density function. A density function closer to the true distribution leads to a better regression performance. In light of this, we propose a novel regression paradigm with Residual Log-likelihood Estimation (RLE) to capture the underlying output distribution. Concretely, RLE learns the change of the distribution instead of the unreferenced underlying distribution to facilitate the training process. With the proposed reparameterization design, our method is compatible with off-the-shelf flow models. The proposed method is effective, efficient and flexible. We show its potential in various human pose estimation tasks with comprehensive experiments. Compared to the conventional regression paradigm, regression with RLE bring 12.4 mAP improvement on MSCOCO without any test-time overhead. Moreover, for the first time, especially on multi-person pose estimation, our regression method is superior to the heatmap-based methods. Our code is available at https://github.com/Jeff-sjtu/res-loglikelihood-regression

3
下载
关闭预览

相关内容

极大似然估计方法(Maximum Likelihood Estimate,MLE)也称为最大概似估计或最大似然估计,是求估计的另一种方法,最大概似是1821年首先由德国数学家高斯(C. F. Gauss)提出,但是这个方法通常被归功于英国的统计学家罗纳德·费希尔(R. A. Fisher) 它是建立在极大似然原理的基础上的一个统计方法,极大似然原理的直观想法是,一个随机试验如有若干个可能的结果A,B,C,... ,若在一次试验中,结果A出现了,那么可以认为实验条件对A的出现有利,也即出现的概率P(A)较大。极大似然原理的直观想法我们用下面例子说明。设甲箱中有99个白球,1个黑球;乙箱中有1个白球.99个黑球。现随机取出一箱,再从抽取的一箱中随机取出一球,结果是黑球,这一黑球从乙箱抽取的概率比从甲箱抽取的概率大得多,这时我们自然更多地相信这个黑球是取自乙箱的。一般说来,事件A发生的概率与某一未知参数theta有关, theta取值不同,则事件A发生的概率P(A/theta)也不同,当我们在一次试验中事件A发生了,则认为此时的theta值应是t的一切可能取值中使P(A/theta)达到最大的那一个,极大似然估计法就是要选取这样的t值作为参数t的估计值,使所选取的样本在被选的总体中出现的可能性为最大。

The Robotics community has started to heavily rely on increasingly realistic 3D simulators for large-scale training of robots on massive amounts of data. But once robots are deployed in the real world, the simulation gap, as well as changes in the real world (e.g. lights, objects displacements) lead to errors. In this paper, we introduce Sim2RealViz, a visual analytics tool to assist experts in understanding and reducing this gap for robot ego-pose estimation tasks, i.e. the estimation of a robot's position using trained models. Sim2RealViz displays details of a given model and the performance of its instances in both simulation and real-world. Experts can identify environment differences that impact model predictions at a given location and explore through direct interactions with the model hypothesis to fix it. We detail the design of the tool, and case studies related to the exploit of the regression to the mean bias and how it can be addressed, and how models are perturbed by the vanish of landmarks such as bikes.

0
0
下载
预览

Blocking, a special case of rerandomization, is routinely implemented in the design stage of randomized experiments to balance baseline covariates. Regression adjustment is highly encouraged in the analysis stage to adjust for the remaining covariate imbalances. Researchers have recommended combining these techniques; however, the research on this combination in a randomization-based inference framework with a large number of covariates is limited. This paper proposes several methods that combine the blocking, rerandomization, and regression adjustment techniques in randomized experiments with high-dimensional covariates. In the design stage, we suggest the implementation of blocking or rerandomization or both techniques to balance a fixed number of covariates most relevant to the outcomes. For the analysis stage, we propose regression adjustment methods based on the Lasso to adjust for the remaining imbalances in the additional high-dimensional covariates. Moreover, we establish the asymptotic properties of the proposed Lasso-adjusted average treatment effect estimators and outline conditions under which these estimators are more efficient than the unadjusted estimators. In addition, we provide conservative variance estimators to facilitate valid inferences. Our analysis is randomization-based, allowing the outcome data generating models to be mis-specified. Simulation studies and two real data analyses demonstrate the advantages of the proposed methods.

0
0
下载
预览

High dimensional non-Gaussian time series data are increasingly encountered in a wide range of applications. Conventional estimation methods and technical tools are inadequate when it comes to ultra high dimensional and heavy-tailed data. We investigate robust estimation of high dimensional autoregressive models with fat-tailed innovation vectors by solving a regularized regression problem using convex robust loss function. As a significant improvement, the dimension can be allowed to increase exponentially with the sample size to ensure consistency under very mild moment conditions. To develop the consistency theory, we establish a new Bernstein type inequality for the sum of autoregressive models. Numerical results indicate a good performance of robust estimates.

0
0
下载
预览

Human pose estimation aims to locate the human body parts and build human body representation (e.g., body skeleton) from input data such as images and videos. It has drawn increasing attention during the past decade and has been utilized in a wide range of applications including human-computer interaction, motion analysis, augmented reality, and virtual reality. Although the recently developed deep learning-based solutions have achieved high performance in human pose estimation, there still remain challenges due to insufficient training data, depth ambiguities, and occlusions. The goal of this survey paper is to provide a comprehensive review of recent deep learning-based solutions for both 2D and 3D pose estimation via a systematic analysis and comparison of these solutions based on their input data and inference procedures. More than 240 research papers since 2014 are covered in this survey. Furthermore, 2D and 3D human pose estimation datasets and evaluation metrics are included. Quantitative performance comparisons of the reviewed methods on popular datasets are summarized and discussed. Finally, the challenges involved, applications, and future research directions are concluded. We also provide a regularly updated project page on: \url{https://github.com/zczcwh/DL-HPE}

0
20
下载
预览

Human pose estimation - the process of recognizing human keypoints in a given image - is one of the most important tasks in computer vision and has a wide range of applications including movement diagnostics, surveillance, or self-driving vehicle. The accuracy of human keypoint prediction is increasingly improved thanks to the burgeoning development of deep learning. Most existing methods solved human pose estimation by generating heatmaps in which the ith heatmap indicates the location confidence of the ith keypoint. In this paper, we introduce novel network structures referred to as multiresolution representation learning for human keypoint prediction. At different resolutions in the learning process, our networks branch off and use extra layers to learn heatmap generation. We firstly consider the architectures for generating the multiresolution heatmaps after obtaining the lowest-resolution feature maps. Our second approach allows learning during the process of feature extraction in which the heatmaps are generated at each resolution of the feature extractor. The first and second approaches are referred to as multi-resolution heatmap learning and multi-resolution feature map learning respectively. Our architectures are simple yet effective, achieving good performance. We conducted experiments on two common benchmarks for human pose estimation: MS-COCO and MPII dataset.

0
5
下载
预览

Cross view feature fusion is the key to address the occlusion problem in human pose estimation. The current fusion methods need to train a separate model for every pair of cameras making them difficult to scale. In this work, we introduce MetaFuse, a pre-trained fusion model learned from a large number of cameras in the Panoptic dataset. The model can be efficiently adapted or finetuned for a new pair of cameras using a small number of labeled images. The strong adaptation power of MetaFuse is due in large part to the proposed factorization of the original fusion model into two parts (1) a generic fusion model shared by all cameras, and (2) lightweight camera-dependent transformations. Furthermore, the generic model is learned from many cameras by a meta-learning style algorithm to maximize its adaptation capability to various camera poses. We observe in experiments that MetaFuse finetuned on the public datasets outperforms the state-of-the-arts by a large margin which validates its value in practice.

0
4
下载
预览

This is an official pytorch implementation of Deep High-Resolution Representation Learning for Human Pose Estimation. In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. The code and models have been publicly available at \url{https://github.com/leoxiaobin/deep-high-resolution-net.pytorch}.

0
5
下载
预览

This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection and video understanding. Our method operates in two-stages: keypoint estimation in frames or short clips, followed by lightweight tracking to generate keypoint predictions linked over the entire video. For frame-level pose estimation we experiment with Mask R-CNN, as well as our own proposed 3D extension of this model, which leverages temporal information over small clips to generate more robust frame predictions. We conduct extensive ablative experiments on the newly released multi-person video pose estimation benchmark, PoseTrack, to validate various design choices of our model. Our approach achieves an accuracy of 55.2% on the validation and 51.8% on the test set using the Multi-Object Tracking Accuracy (MOTA) metric, and achieves state of the art performance on the ICCV 2017 PoseTrack keypoint tracking challenge.

0
5
下载
预览

Estimating the head pose of a person is a crucial problem that has a large amount of applications such as aiding in gaze estimation, modeling attention, fitting 3D models to video and performing face alignment. Traditionally head pose is computed by estimating some keypoints from the target face and solving the 2D to 3D correspondence problem with a mean human head model. We argue that this is a fragile method because it relies entirely on landmark detection performance, the extraneous head model and an ad-hoc fitting step. We present an elegant and robust way to determine pose by training a multi-loss convolutional neural network on 300W-LP, a large synthetically expanded dataset, to predict intrinsic Euler angles (yaw, pitch and roll) directly from image intensities through joint binned pose classification and regression. We present empirical tests on common in-the-wild pose benchmark datasets which show state-of-the-art results. Additionally we test our method on a dataset usually used for pose estimation using depth and start to close the gap with state-of-the-art depth pose methods. We open-source our training and testing code as well as release our pre-trained models.

0
5
下载
预览

The task of multi-person human pose estimation in natural scenes is quite challenging. Existing methods include both top-down and bottom-up approaches. The main advantage of bottom-up methods is its excellent tradeoff between estimation accuracy and computational cost. We follow this path and aim to design smaller, faster, and more accurate neural networks for the regression of keypoints and limb association vectors. These two regression tasks are naturally dependent on each other. In this work, we propose a dual-path network specially designed for multi-person human pose estimation, and compare our performance with the openpose network in aspects of model size, forward speed, and estimation accuracy.

0
3
下载
预览
小贴士
相关论文
Theo Jaunet,Guillaume Bono,Romain Vuillemot,Christian Wolf
0+阅读 · 9月24日
Linbo Liu,Danna Zhang
0+阅读 · 9月21日
Ce Zheng,Wenhan Wu,Taojiannan Yang,Sijie Zhu,Chen Chen,Ruixu Liu,Ju Shen,Nasser Kehtarnavaz,Mubarak Shah
20+阅读 · 2020年12月24日
Simple Multi-Resolution Representation Learning for Human Pose Estimation
Trung Q. Tran,Giang V. Nguyen,Daeyoung Kim
5+阅读 · 2020年4月14日
MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation
Rongchang Xie,Chunyu Wang,Yizhou Wang
4+阅读 · 2020年3月30日
Ke Sun,Bin Xiao,Dong Liu,Jingdong Wang
5+阅读 · 2019年2月25日
Rohit Girdhar,Georgia Gkioxari,Lorenzo Torresani,Manohar Paluri,Du Tran
5+阅读 · 2018年5月2日
Nataniel Ruiz,Eunji Chong,James M. Rehg
5+阅读 · 2018年4月13日
Guanghan Ning,Zhihai He
3+阅读 · 2017年10月27日
相关VIP内容
专知会员服务
61+阅读 · 2020年11月20日
专知会员服务
99+阅读 · 2020年3月12日
[综述]深度学习下的场景文本检测与识别
专知会员服务
45+阅读 · 2019年10月10日
机器学习入门的经验与建议
专知会员服务
47+阅读 · 2019年10月10日
TensorFlow 2.0 学习资源汇总
专知会员服务
46+阅读 · 2019年10月9日
相关资讯
CVPR 2019 | 34篇 CVPR 2019 论文实现代码
AI科技评论
20+阅读 · 2019年6月23日
已删除
将门创投
3+阅读 · 2019年6月12日
Hierarchically Structured Meta-learning
CreateAMind
12+阅读 · 2019年5月22日
Transferring Knowledge across Learning Processes
CreateAMind
8+阅读 · 2019年5月18日
Unsupervised Learning via Meta-Learning
CreateAMind
32+阅读 · 2019年1月3日
Top