通过像素的集体贡献解释目标检测器
Explaining Object Detectors via Collective Contribution of Pixels
AI总结：
本文提出基于Shapley值和交互的游戏理论方法，以捕捉像素的个体和集体贡献，提升目标检测器的解释性与准确性。
摘要：
视觉解释对于增强目标检测器的可靠性至关重要。目标检测器通过评估多个视觉特征的集体信息来识别和定位实例。在生成解释时，忽视这些集体影响可能导致遗漏组成线索或捕捉虚假相关性。然而，现有方法通常仅关注单个像素贡献，忽视了多个像素的集体贡献。为了解决这一限制，我们提出了一种基于Shapley值和交互的游戏理论方法，以显式捕捉个体和集体像素贡献。我们的方法为边界框定位和类别确定提供解释，突出对检测至关重要的区域。广泛实验表明，所提出的方法在识别重要区域的准确性上优于最先进的方法。代码可在https://github.com/tttt-0814/VX-CODE获取。
英文摘要：
Visual explanations for object detectors are crucial for enhancing their reliability. Object detectors identify and localize instances by assessing multiple visual features collectively. When generating explanations, overlooking these collective influences in detections may lead to missing compositional cues or capturing spurious correlations. However, existing methods typically focus solely on individual pixel contributions, neglecting the collective contribution of multiple pixels. To address this limitation, we propose a game-theoretic method based on Shapley values and interactions to explicitly capture both individual and collective pixel contributions. Our method provides explanations for both bounding box localization and class determination, highlighting regions crucial for detection. Extensive experiments demonstrate that the proposed method identifies important regions more accurately than state-of-the-art methods. The code is available at https://github.com/tttt-0814/VX-CODE
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
