mlsanityData to 14 Oct 2026

DP-Net: Learning Discriminative Parts for image recognition

arXiv 2404.15037 ↗First posted 23 Apr 2024cs.CVcited by 2

Not on the map. Why?

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.

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

17 of 29 references.

References · 17

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  2. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  3. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  4. 2016The Mythos of Model Interpretabilitycited by 721
  5. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 214
  6. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  7. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
  8. 2014The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classificationcited by 67
  9. 2015Part-Stacked CNN for Fine-Grained Visual Categorizationcited by 62
  10. 2014Deformable Part Models are Convolutional Neural Networkscited by 35
  11. 2015Contextual Action Recognition with R*CNNcited by 34
  12. 2019Scene Recognition with Prototype-agnostic Scene Layoutcited by 17
5 more
  1. 2016Fully Convolutional Attention Networks for Fine-Grained Recognitioncited by 8
  2. 2017Unsupervised part learning for visual recognitioncited by 3
  3. 2014Automatic Discovery and Optimization of Parts for Image Classificationcited by 2
  4. 2016Automatic discovery of discriminative parts as a quadratic assignment problemcited by 2
  5. 2015No Spare Parts: Sharing Part Detectors for Image Categorizationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Component-Based Out-of-Distribution Detectioncited by 0
  2. 2026Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbationscited by 0