# Adaptive Dilated Convolution For Human Pose Estimation

arXiv: https://arxiv.org/abs/2107.10477 · HTML: https://mlsanity.com/paper/2107.10477/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 22 Jul 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection](https://mlsanity.com/paper/1904.07392/) (2019)
- [A guide to convolution arithmetic for deep learning](https://mlsanity.com/paper/1603.07285/) (2016)
- [Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation](https://mlsanity.com/paper/2012.15175/) (2020)
- [Learning Delicate Local Representations for Multi-Person Pose Estimation](https://mlsanity.com/paper/2003.04030/) (2020)
- [Rethinking on Multi-Stage Networks for Human Pose Estimation](https://mlsanity.com/paper/1901.00148/) (2019)
- [Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation](https://mlsanity.com/paper/1707.05388/) (2017)
- [Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information](https://mlsanity.com/paper/1905.03466/) (2019)
- [Deep Feature Pyramid Reconfiguration for Object Detection](https://mlsanity.com/paper/1808.07993/) (2018)
- [Efficient Human Pose Estimation by Learning Deeply Aggregated Representations](https://mlsanity.com/paper/2012.07033/) (2020)

## 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.