# PDiscoNet: Semantically consistent part discovery for fine-grained recognition

arXiv: https://arxiv.org/abs/2309.03173 · HTML: https://mlsanity.com/paper/2309.03173/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 6 Sep 2023.

## Builds on (most cited first, 29 of 29)

- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [PartImageNet: A Large, High-Quality Dataset of Parts](https://mlsanity.com/paper/2112.00933/) (2021)
- [SCOPS: Self-Supervised Co-Part Segmentation](https://mlsanity.com/paper/1905.01298/) (2019)
- [B-cos Networks: Alignment is All We Need for Interpretability](https://mlsanity.com/paper/2205.10268/) (2022)
- [Interpretable and Accurate Fine-grained Recognition via Region Grouping](https://mlsanity.com/paper/2005.10411/) (2020)
- [Unsupervised Discovery of Object Landmarks as Structural Representations](https://mlsanity.com/paper/1804.04412/) (2018)
- [Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up](https://mlsanity.com/paper/1903.02827/) (2019)
- [Deep Feature Factorization For Concept Discovery](https://mlsanity.com/paper/1806.10206/) (2018)
- [Part-Stacked CNN for Fine-Grained Visual Categorization](https://mlsanity.com/paper/1512.08086/) (2015)
- [Unsupervised Part Discovery from Contrastive Reconstruction](https://mlsanity.com/paper/2111.06349/) (2021)
- [Convolutional Dynamic Alignment Networks for Interpretable Classifications](https://mlsanity.com/paper/2104.00032/) (2021)
- [The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition](https://mlsanity.com/paper/1511.06789/) (2015)
- [Part-Based Models Improve Adversarial Robustness](https://mlsanity.com/paper/2209.09117/) (2022)
- [Localizing by Describing: Attribute-Guided Attention Localization for Fine-Grained Recognition](https://mlsanity.com/paper/1605.06217/) (2016)

## Built on by (most cited first, 21 of 21)

- [LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision](https://mlsanity.com/paper/2405.14331/) (2024)
- [Low-Resource Vision Challenges for Foundation Models](https://mlsanity.com/paper/2401.04716/) (2024)
- [Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement](https://mlsanity.com/paper/2507.06928/) (2025)
- [Interpretable Image Classification via Non-parametric Part Prototype Learning](https://mlsanity.com/paper/2503.10247/) (2025)
- [PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers](https://mlsanity.com/paper/2407.04538/) (2024)
- [SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions](https://mlsanity.com/paper/2507.23784/) (2025)
- [PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation](https://mlsanity.com/paper/2603.17520/) (2026)
- [CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models](https://mlsanity.com/paper/2412.19331/) (2024)
- [Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation](https://mlsanity.com/paper/2501.09688/) (2025)
- [Understanding Multi-Granularity for Open-Vocabulary Part Segmentation](https://mlsanity.com/paper/2406.11384/) (2024)
- [Unsupervised Part Discovery via Dual Representation Alignment](https://mlsanity.com/paper/2408.08108/) (2024)
- [AIM: Amending Inherent Interpretability via Self-Supervised Masking](https://mlsanity.com/paper/2508.11502/) (2025)
- [Disentangling Visual Transformers: Patch-level Interpretability for Image Classification](https://mlsanity.com/paper/2502.17196/) (2025)
- [Two-stage Vision Transformers and Hard Masking offer Robust Object Representations](https://mlsanity.com/paper/2506.08915/) (2025)
- [Comprehensive Evaluation of Prototype Neural Networks](https://mlsanity.com/paper/2507.06819/) (2025)
- [Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints](https://mlsanity.com/paper/2507.11985/) (2025)
- [Domain-invariant Representation Learning via Segment Anything Model for Blood Cell Classification](https://mlsanity.com/paper/2408.07467/) (2024)
- [Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selection](https://mlsanity.com/paper/2511.12992/) (2025)
- [Metonymy in vision models undermines attention-based interpretability](https://mlsanity.com/paper/2605.06095/) (2026)
- [Spatially Grounded Concept Bottleneck Models via Part-Factorized Attention](https://mlsanity.com/paper/2606.04364/) (2026)
- [OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification](https://mlsanity.com/paper/2608.30003/) (2026)

## Abstract (arXiv)

Fine-grained classification often requires recognizing specific object parts, such as beak shape and wing patterns for birds. Encouraging a fine-grained classification model to first detect such parts and then using them to infer the class could help us gauge whether the model is indeed looking at the right details better than with interpretability methods that provide a single attribution map. We propose PDiscoNet to discover object parts by using only image-level class labels along with priors encouraging the parts to be: discriminative, compact, distinct from each other, equivariant to rigid transforms, and active in at least some of the images. In addition to using the appropriate losses to encode these priors, we propose to use part-dropout, where full part feature vectors are dropped at once to prevent a single part from dominating in the classification, and part feature vector modulation, which makes the information coming from each part distinct from the perspective of the classifier. Our results on CUB, CelebA, and PartImageNet show that the proposed method provides substantially better part discovery performance than previous methods while not requiring any additional hyper-parameter tuning and without penalizing the classification performance. The code is available at https://github.com/robertdvdk/part_detection.