W-Net: Reinforced U-Net for Density Map Estimation

TL;DR

This paper introduces W-Net, a reinforced U-Net architecture with an independent decoding branch for improved crowd density map estimation, achieving state-of-the-art results and highlighting current limitations in crowd counting methods.

Contribution

The paper proposes a novel reinforced U-Net model with an independent decoding branch, enhancing convergence and density map quality for crowd counting.

Findings

Achieves state-of-the-art crowd counting results.

The independent decoding branch improves convergence and SSIM.

Current methods are reaching performance saturation, with unresolved challenges.

Abstract

Crowd management is of paramount importance when it comes to preventing stampedes and saving lives, especially in a countries like China and India where the combined population is a third of the global population. Millions of people convene annually all around the nation to celebrate a myriad of events and crowd count estimation is the linchpin of the crowd management system that could prevent stampedes and save lives. We present a network for crowd counting which reports state of the art results on crowd counting benchmarks. Our contributions are, first, a U-Net inspired model which affords us to report state of the art results. Second, we propose an independent decoding Reinforcement branch which helps the network converge much earlier and also enables the network to estimate density maps with high Structural Similarity Index (SSIM). Third, we discuss the drawbacks of the contemporary architectures and empirically show that even though our architecture achieves state of the art results, the merit may be due to the encoder-decoder pipeline instead. Finally, we report the error analysis which shows that the contemporary line of work is at saturation and leaves certain prominent problems unsolved.