# DP-Net: Learning Discriminative Parts for image recognition

arXiv: https://arxiv.org/abs/2404.15037 · HTML: https://mlsanity.com/paper/2404.15037/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Builds on (most cited first, 17 of 17)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Interpretable Image Classification with Differentiable Prototypes Assignment](https://mlsanity.com/paper/2112.02902/) (2021)
- [ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery](https://mlsanity.com/paper/2011.14340/) (2020)
- [The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification](https://mlsanity.com/paper/1411.6447/) (2014)
- [Part-Stacked CNN for Fine-Grained Visual Categorization](https://mlsanity.com/paper/1512.08086/) (2015)
- [Deformable Part Models are Convolutional Neural Networks](https://mlsanity.com/paper/1409.5403/) (2014)
- [Contextual Action Recognition with R*CNN](https://mlsanity.com/paper/1505.01197/) (2015)
- [Scene Recognition with Prototype-agnostic Scene Layout](https://mlsanity.com/paper/1909.03234/) (2019)
- [Fully Convolutional Attention Networks for Fine-Grained Recognition](https://mlsanity.com/paper/1603.06765/) (2016)
- [Unsupervised part learning for visual recognition](https://mlsanity.com/paper/1704.03755/) (2017)
- [Automatic Discovery and Optimization of Parts for Image Classification](https://mlsanity.com/paper/1412.6598/) (2014)
- [Automatic discovery of discriminative parts as a quadratic assignment problem](https://mlsanity.com/paper/1611.04413/) (2016)
- [No Spare Parts: Sharing Part Detectors for Image Categorization](https://mlsanity.com/paper/1510.04908/) (2015)

## Built on by (most cited first, 2 of 2)

- [Component-Based Out-of-Distribution Detection](https://mlsanity.com/paper/2604.21546/) (2026)
- [Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations](https://mlsanity.com/paper/2609.38625/) (2026)

## Abstract (arXiv)

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.