Fast Human Pose Estimation

By Feng Zhang, Xiatian Zhu, Mao Ye. 2018

283 citations recorded by the source corpus.

Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this work, we investigate the under-studied but practically critical pose model efficiency problem. To this end, we present a new Fast Pose Distillation (FPD) model learning strategy. Specifically, the FPD trains a lightweight pose neural network architecture capable of executing rapidly with low computational cost. It is achieved by effectively transferring the pose structure knowledge of a strong teacher network. Extensive evaluations demonstrate the advantages of our FPD method over a broad range of state-of-the-art pose estimation approaches in terms of model cost-effectiveness on two standard benchmark datasets, MPII Human Pose and Leeds Sports Pose.

Subfields: Computer Vision and Pattern Recognition, Endocrinology, Diabetes and Metabolism, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Endocrinology, Diabetes and Metabolism

In Human-Computer Interaction

Citations in the corpus

Knowledge Distillation: A Survey (2020, methodology): “knowledge and distillation, the relationship between the structures of the teacher and the student also signiﬁcantly inﬂuences the performance of knowledge distillation. For example, as described in (Zhang et al., 2019b), the student model may learn very little from some teacher models. This is caus”
Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression (2021, methodology): “The convolutional neural network (CNN) solutions [17, 35, 56, 70, 43, 45, 49, 74, 54] to human pose estimation have shown superior performance over the conventional methods, such as the probabilistic graphical model or the pictorial structure model [72, 50].”
Deep Learning-based Human Pose Estimation: A Survey (2020, methodology): “, [18, 55, 117, 119, 148, 149, 154, 155, 173, 179, 191, 223, 234, 285]) to predict joint coordinates from images as shown in Fig.”
Distribution-Aware Coordinate Representation for Human Pose Estimation (2019, methodology): “The state-of-the-art pose methods [20, 33, 25, 38] are based on the heatmap coordinate representation.”
Monocular human pose estimation: A survey of deep learning-based methods (2020, methodology): “…(4) Temporal constraint : (Jain et al., 2014; Pﬁster et al., 2015; Luo et al., 2018) (5) Network compression : (Tang et al., 2018b; Debnath et al., 2018; Feng et al., 2019) 2D Multiple Top-down coarse-to-ﬁne (Iqbal and Gall, 2016; Huang et al., 2017), bounding box reﬁnement (Fang et al., 2017),…”
MotionBERT: A Unified Perspective on Learning Human Motion Representations (2022, background): “[124] predict future 3D dynamics in a self-supervised manner.”
Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference (2019, methodology): “Our models achieve similar performance as FPD [52] (without knowledge distillation) with fewer computations.”
Interactive Knowledge Distillation (2020, background): “To reduce the resource consumption while maintaining good performance, researchers leverage knowledge distillation techniques [30,6,9,10] to transfer informative knowledge from a cumbersome but well-trained teacher network into a light-weight but unskilled student network.”
Source-Free Domain Adaptation for Semantic Segmentation (2021, background): “Since then, a variety of KD methods has been presented for model compression [28, 2, 50, 32], domain adaptation [52, 53], and multi-modal learning [51, 14, 10].”
Monocular depth estimation based on deep learning: An overview (2020, methodology): “based methods: With the rapid development in deep learning, deep neural networks show their outstanding performance on image processing, like image classiﬁcation arXiv:2003.06620v2 [cs.CV] 3 Jul 2020 [20], objective detection [21] and semantic segmentation [22], etc, and related well-written overvie”