We propose the gradient-weighted Object Detector Activation Maps (ODAM), a visualized explanation technique for interpreting the predictions of object detectors. Utilizing the gradients of detector targets flowing into the intermediate feature maps, ODAM produces heat maps that show the influence of regions on the detector's decision for each predicted attribute. Compared to previous works classification activation maps (CAM), ODAM generates instance-specific explanations rather than class-specific ones. We show that ODAM is applicable to both one-stage detectors and two-stage detectors with different types of detector backbones and heads, and produces higher-quality visual explanations than the state-of-the-art both effectively and efficiently. We next propose a training scheme, Odam-Train, to improve the explanation ability on object discrimination of the detector through encouraging consistency between explanations for detections on the same object, and distinct explanations for detections on different objects. Based on the heat maps produced by ODAM with Odam-Train, we propose Odam-NMS, which considers the information of the model's explanation for each prediction to distinguish the duplicate detected objects. We present a detailed analysis of the visualized explanations of detectors and carry out extensive experiments to validate the effectiveness of the proposed ODAM.

翻译：我们提出梯度加权目标检测器激活图（ODAM），这是一种用于解释目标检测器预测结果的可视化解释技术。通过利用检测器目标流入中间特征图的梯度，ODAM生成热力图，展示各区域对检测器每个预测属性的决策影响程度。与以往的分类激活图（CAM）方法相比，ODAM生成的是实例特定解释而非类别特定解释。我们证明ODAM可适用于单阶段检测器和双阶段检测器，兼容不同类型的检测器骨干网络和头部结构，并能高效生成优于现有技术的高质量可视化解释。我们进一步提出训练方案Odam-Train，通过强化同一目标检测结果之间的一致性解释以及不同目标检测结果之间的区分性解释，提升检测器在目标判别方面的解释能力。基于ODAM结合Odam-Train生成的热力图，我们提出Odam-NMS，该方案利用模型对每个预测结果的解释信息来区分重复检测的目标。我们对检测器的可视化解释进行详细分析，并通过大量实验验证所提出ODAM的有效性。