DP-Net: Learning Discriminative Parts for image recognition

arXiv:2404.15037v1 Announce Type: new
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 …

abstract architecture arxiv capabilities cnn convolutional neural network cs.cv exploits fine-tuning image image recognition images interpretation network neural network paper part recognition type