PixelGame: Infrared small target segmentation as a Nash equilibrium

TL;DR

PixelGame introduces a novel game-theoretic framework for infrared small target segmentation, modeling false positives and negatives as competing players to achieve optimal detection via Nash equilibrium.

Contribution

The paper presents a new competitive game framework for ISTS, utilizing Nash equilibrium to balance false positives and negatives, and introduces maximum information modulation for better target highlighting.

Findings

Outperforms state-of-the-art methods in F1-measure and IoU.

Effective in highlighting small targets with MIM.

Validated on two public datasets.

Abstract

A key challenge of infrared small target segmentation (ISTS) is to balance false negative pixels (FNs) and false positive pixels (FPs). Traditional methods combine FNs and FPs into a single objective by weighted sum, and the optimization process is decided by one actor. Minimizing FNs and FPs with the same strategy leads to antagonistic decisions. To address this problem, we propose a competitive game framework (pixelGame) from a novel perspective for ISTS. In pixelGame, FNs and FPs are controlled by different player whose goal is to minimize their own utility function. FNs-player and FPs-player are designed with different strategies: One is to minimize FNs and the other is to minimize FPs. The utility function drives the evolution of the two participants in competition. We consider the Nash equilibrium of pixelGame as the optimal solution. In addition, we propose maximum information modulation (MIM) to highlight the tar-get information. MIM effectively focuses on the salient region including small targets. Extensive experiments on two standard public datasets prove the effectiveness of our method. Compared with other state-of-the-art methods, our method achieves better performance in terms of F1-measure (F1) and the intersection of union (IoU).