mlsanityData to 7 Oct 2026

Adaptive Dilated Convolution For Human Pose Estimation

arXiv 2107.10477 ↗First posted 22 Jul 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Most existing human pose estimation (HPE) methods exploit multi-scale information by fusing feature maps of four different spatial sizes, ie 1/4, 1/8, 1/16, and 1/32 of the input image. There are two drawbacks of this strategy: 1) feature maps of different spatial sizes may be not well aligned spatially, which potentially hurts the accuracy of keypoint location; 2) these scales are fixed and inflexible, which may restrict the generalization ability over various human sizes. Towards these issues, we propose an adaptive dilated convolution (ADC). It can generate and fuse multi-scale features of the same spatial sizes by setting different dilation rates for different channels. More importantly, these dilation rates are generated by a regression module. It enables ADC to adaptively adjust the fused scales and thus ADC may generalize better to various human sizes. ADC can be end-to-end trained and easily plugged into existing methods. Extensive experiments show that ADC can bring consistent improvements to various HPE methods. The source codes will be released for further research.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 34 references that are in the map. First posted on arXiv 22 Jul 2021.

Builds on

26 of 34 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  9. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  10. 2017Deformable Convolutional Networkscited by 1,481
  11. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  12. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
14 more
  1. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  2. 2018Path Aggregation Network for Instance Segmentationcited by 796
  3. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  4. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  5. 2016Convolutional Pose Machinescited by 325
  6. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  7. 2016A guide to convolution arithmetic for deep learningcited by 182
  8. 2020Rethinking the Heatmap Regression for Bottom-up Human Pose Estimationcited by 69
  9. 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
  10. 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
  11. 2017Benchmarking and Error Diagnosis in Multi-Instance Pose Estimationcited by 48
  12. 2019Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Informationcited by 35
  13. 2018Deep Feature Pyramid Reconfiguration for Object Detectioncited by 23
  14. 2020Efficient Human Pose Estimation by Learning Deeply Aggregated Representationscited by 4

Built on by

Not cited yet.