AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation

2020-08-16 · Xinyu Gong, Wuyang Chen, Yifan Jiang, Ye Yuan, Xian-Ming Liu, Qian Zhang, Yuan Li, Zhangyang Wang

We present AutoPose, a novel neural architecture search(NAS) framework that is capable of automatically discovering multiple parallel branches of cross-scale connections towards accurate and high-resolution 2D human pose estimation. Recently, high-performance hand-crafted convolutional networks for pose estimation show growing demands on multi-scale fusion and high-resolution representations. However, current NAS works exhibit limited flexibility on scale searching, they dominantly adopt simplified search spaces of single-branch architectures. Such simplification limits the fusion of information at different scales and fails to maintain high-resolution representations. The presentedAutoPose framework is able to search for multi-branch scales and network depth, in addition to the cell-level microstructure. Motivated by the search space, a novel bi-level optimization method is presented, where the network-level architecture is searched via reinforcement learning, and the cell-level search is conducted by the gradient-based method. Within 2.5 GPU days, AutoPose is able to find very competitive architectures on the MS COCO dataset, that are also transferable to the MPII dataset. Our code is available at https://github.com/VITA-Group/AutoPose.

📄 PDF Abstract BibTeX arXiv:2008.07018

Code (0)

등록된 구현이 없습니다.

Tasks

2D Human Pose EstimationGPUNeural Architecture Search Pose Estimation

Recurrent Aggregation Learning for Multi-View Echocardiographic Sequences Segmentation

2019-07-24 · Ming Li, Weiwei Zhang, Guang Yang, Chengjia Wang 외

Multi-view echocardiographic sequences segmentation is crucial for clinical diagnosis. However, this task is challenging due to limited labeled data, huge noise, and large gaps across views. Here we propose a recurrent a…

Classification General Classification Segmentation

MVP-Net: Multiple View Pointwise Semantic Segmentation of Large-Scale Point Clouds

2022-01-30 · Chuanyu Luo, Xiaohan Li, Nuo Cheng, Han Li 외

Semantic segmentation of 3D point cloud is an essential task for autonomous driving environment perception. The pipeline of most pointwise point cloud semantic segmentation methods includes points sampling, neighbor sear…

Autonomous Driving Segmentation Semantic Segmentation

UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation

2020-09-16 · Yuanfeng Ji, Ruimao Zhang, Zhen Li, Jiamin Ren 외

Aggregating multi-level feature representation plays a critical role in achieving robust volumetric medical image segmentation, which is important for the auxiliary diagnosis and treatment. Unlike the recent neural archi…

Decoder Image Segmentation Medical Image Segmentation Neural Architecture Search+3

On the Stability of Multi-branch Network

2021-01-01 · Huishuai Zhang, Da Yu, Wei Chen, Tie-Yan Liu

Multi-branch architectures are widely used in state-of-the-art neural networks. Their empirical success relies on some design wisdom, like adding normalization layers or/and scaling down the initialization. In this pap…

Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes

2022-03-08 · Xi Weng, Yan Yan, Genshun Dong, Chang Shu 외

Real-time semantic segmentation, which aims to achieve high segmentation accuracy at real-time inference speed, has received substantial attention over the past few years. However, many state-of-the-art real-time semanti…

Decoder GPU Real-Time Semantic Segmentation Segmentation+1