论文标题
通过像素的预测来迈向可解释且可解释的手工检测
Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction
论文作者
论文摘要
现有基于CNN的手部检测方法的解释性缺乏可解释性，因此很难理解其预测背后的基本原理。在本文中，我们提出了一种新型的神经网络模型，该模型首次将可解释性引入了手工检测。主要改进包括：（1）在像素级别检测手，以解释哪些像素是其决策的基础并提高模型的透明度。 （2）可解释的高光特征融合块突出了多个层之间的独特特征，并学会了歧视性的特征以获得稳健的性能。 （3）我们引入了一个透明的表示，即旋转图，以学习旋转特征，而不是复杂和非透明旋转和偏移层。 （4）辅助监督加速了训练过程，这在我们的实验中节省了10个小时以上。与具有更高速度的最新方法相比，VIVA和牛津手部检测和跟踪数据集的实验结果显示出我们方法的竞争精度。
The lack of interpretability of existing CNN-based hand detection methods makes it difficult to understand the rationale behind their predictions. In this paper, we propose a novel neural network model, which introduces interpretability into hand detection for the first time. The main improvements include: (1) Detect hands at pixel level to explain what pixels are the basis for its decision and improve transparency of the model. (2) The explainable Highlight Feature Fusion block highlights distinctive features among multiple layers and learns discriminative ones to gain robust performance. (3) We introduce a transparent representation, the rotation map, to learn rotation features instead of complex and non-transparent rotation and derotation layers. (4) Auxiliary supervision accelerates the training process, which saves more than 10 hours in our experiments. Experimental results on the VIVA and Oxford hand detection and tracking datasets show competitive accuracy of our method compared with state-of-the-art methods with higher speed.
