High-Resolution Representations for Labeling Pixels and Regions

TL;DR

This paper enhances high-resolution neural network architectures by aggregating multi-resolution features, leading to improved performance across various vision tasks like segmentation, landmark detection, and object detection.

Contribution

The paper introduces a simple modification to HRNet that aggregates features from all resolutions, significantly improving performance on multiple vision benchmarks.

Findings

Achieved top results in semantic segmentation on Cityscapes, LIP, and PASCAL Context.

Outperformed existing models in facial landmark detection on multiple datasets.

Surpassed state-of-the-art in COCO object detection with the proposed multi-resolution approach.

Abstract

High-resolution representation learning plays an essential role in many vision problems, e.g., pose estimation and semantic segmentation. The high-resolution network (HRNet)~\cite{SunXLW19}, recently developed for human pose estimation, maintains high-resolution representations through the whole process by connecting high-to-low resolution convolutions in \emph{parallel} and produces strong high-resolution representations by repeatedly conducting fusions across parallel convolutions. In this paper, we conduct a further study on high-resolution representations by introducing a simple yet effective modification and apply it to a wide range of vision tasks. We augment the high-resolution representation by aggregating the (upsampled) representations from all the parallel convolutions rather than only the representation from the high-resolution convolution as done in~\cite{SunXLW19}. This simple modification leads to stronger representations, evidenced by superior results. We show top results in semantic segmentation on Cityscapes, LIP, and PASCAL Context, and facial landmark detection on AFLW, COFW, $300$W, and WFLW. In addition, we build a multi-level representation from the high-resolution representation and apply it to the Faster R-CNN object detection framework and the extended frameworks. The proposed approach achieves superior results to existing single-model networks on COCO object detection. The code and models have been publicly available at \url{https://github.com/HRNet}.