Discrete-Constrained Regression for Local Counting Models
This addresses the issue of sensitivity to annotation errors in regression models for tasks like crowd counting and age estimation, offering an incremental improvement over existing approaches.
The paper tackled the problem that classification outperforms regression for local counting tasks by identifying imprecise ground truth as the cause, and proposed discrete-constrained regression, which achieved higher accuracy than both methods on crowd counting benchmarks and age estimation.
Local counts, or the number of objects in a local area, is a continuous value by nature. Yet recent state-of-the-art methods show that formulating counting as a classification task performs better than regression. Through a series of experiments on carefully controlled synthetic data, we show that this counter-intuitive result is caused by imprecise ground truth local counts. Factors such as biased dot annotations and incorrectly matched Gaussian kernels used to generate ground truth counts introduce deviations from the true local counts. Standard continuous regression is highly sensitive to these errors, explaining the performance gap between classification and regression. To mitigate the sensitivity, we loosen the regression formulation from a continuous scale to a discrete ordering and propose a novel discrete-constrained (DC) regression. Applied to crowd counting, DC-regression is more accurate than both classification and standard regression on three public benchmarks. A similar advantage also holds for the age estimation task, verifying the overall effectiveness of DC-regression.