PLRF-NMS: A Piecewise Linear Rational Function in Non-Maximum Suppression

Ivar Persson, Håkan Ardö, Mikael Nilsson

Abstract: Activation functions are fundamental components in neural networks, enabling non-linear transformations essential for tasks like signal processing, control systems, image analysis, economics, and robotics. They play a crucial role in facilitating processes such as noise reduction, segmentation, and decision-making across various applications. Splines offer an alternative approach to traditional activation functions (e.g., ReLU or Sigmoid), providing flexibility and adaptability to enhance function approximation. In this work a specific spline, the Piecewise Linear Fractional Function (PLRF), is introduced and proposed as a re-scoring mechanism for soft Non-Maximum Suppression (NMS) in object detection pipelines. The PLRF is parametrized with up to four hyperparameters within the range (0, 1) and the paper presents two black-box optimization techniques, GridFib and HybridNM, to refine hyperparameters. Experimental results on two different datasets indicate that the PLRF achieves higher scores compared to Greedy-NMS and Soft-NMS methods. Furthermore, the number of function evaluations needed with the proposed optimization methods reduces computational evaluations needed relative to the Bayesian optimization technique commonly used in this context.

External IDs:doi:10.1007/978-3-032-05060-1_29