Multi-Person Pose Estimation with Enhanced Feature Aggregation and Selection

TL;DR

This paper introduces EFASNet, a novel network for multi-person 2D pose estimation that enhances feature aggregation and selection, leading to more accurate joint localization in crowded scenes.

Contribution

The paper presents a new EFASNet architecture with a Feature Aggregation and Selection Module, a feature fusion strategy, and a Dense Upsampling Convolution module, improving pose estimation accuracy.

Findings

Outperforms state-of-the-art methods on CrowdPose, COCO, and MPII datasets.

Achieves higher accuracy in crowded and occluded scenes.

Demonstrates robustness and superior performance across benchmarks.

Abstract

We propose a novel Enhanced Feature Aggregation and Selection network (EFASNet) for multi-person 2D human pose estimation. Due to enhanced feature representation, our method can well handle crowded, cluttered and occluded scenes. More specifically, a Feature Aggregation and Selection Module (FASM), which constructs hierarchical multi-scale feature aggregation and makes the aggregated features discriminative, is proposed to get more accurate fine-grained representation, leading to more precise joint locations. Then, we perform a simple Feature Fusion (FF) strategy which effectively fuses high-resolution spatial features and low-resolution semantic features to obtain more reliable context information for well-estimated joints. Finally, we build a Dense Upsampling Convolution (DUC) module to generate more precise prediction, which can recover missing joint details that are usually unavailable in common upsampling process. As a result, the predicted keypoint heatmaps are more accurate. Comprehensive experiments demonstrate that the proposed approach outperforms the state-of-the-art methods and achieves the superior performance over three benchmark datasets: the recent big dataset CrowdPose, the COCO keypoint detection dataset and the MPII Human Pose dataset. Our code will be released upon acceptance.