Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling

TL;DR

This paper introduces a semi-supervised crowd counting method that models pixel-wise density as a probability distribution, improving accuracy with limited labeled data through novel loss functions and self-supervised learning.

Contribution

It proposes a pixel-wise density distribution modeling approach, a distribution matching loss, and a density token-enhanced transformer decoder for semi-supervised crowd counting.

Findings

Outperforms existing methods on four datasets.

Effective with limited labeled data.

Significantly improves counting accuracy.

Abstract

This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled. We formulate the pixel-wise density value to regress as a probability distribution, instead of a single deterministic value. On this basis, we propose a semi-supervised crowd-counting model. Firstly, we design a pixel-wise distribution matching loss to measure the differences in the pixel-wise density distributions between the prediction and the ground truth; Secondly, we enhance the transformer decoder by using density tokens to specialize the forwards of decoders w.r.t. different density intervals; Thirdly, we design the interleaving consistency self-supervised learning mechanism to learn from unlabeled data efficiently. Extensive experiments on four datasets are performed to show that our method clearly outperforms the competitors by a large margin under various labeled ratio settings. Code will be released at https://github.com/LoraLinH/Semi-supervised-Counting-via-Pixel-by-pixel-Density-Distribution-Modelling.