Abstract
This paper presents Discriminative Part Network (DP-Net), a deep architecture with strong interpretation capabilities, which exploits a pretrained Convolutional Neural Network (CNN) combined with a part-based recognition module. This system learns and detects parts in the images that are discriminative among categories, without the need for fine-tuning the CNN, making it more scalable than other part-based models. While part-based approaches naturally offer interpretable representations, we propose explanations at image and category levels and introduce specific constraints on the part learning process to make them more discrimative.
Abstract (translated)
本文介绍了一种名为Discriminative Part Network(DP-Net)的深度架构,具有很强的解释能力,它利用了一个预训练的卷积神经网络(CNN)和一个基于部分的识别模块。通过结合预训练的CNN和基于部分的识别模块,该系统可以学习并检测图像中不同分类之间的判别性部分,而无需对CNN进行微调,使其比其他基于部分的应用更具有可扩展性。 尽管基于部分的方法可以提供可解释的表示,但我们提出了在图像和分类级别解释器和特定对部分学习过程的限制,以使其更具判别性。
URL
https://arxiv.org/abs/2404.15037