DP-Net: Learning Discriminative Parts for image recognition
This work addresses interpretability in image recognition for computer vision applications, but it is incremental as it builds on existing part-based approaches.
The paper tackles image recognition by introducing DP-Net, a deep architecture that learns discriminative parts without fine-tuning a pretrained CNN, achieving more scalable and interpretable results compared to other part-based models.
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.