# PARTICUL: Part Identification with Confidence measure using Unsupervised Learning

arXiv: https://arxiv.org/abs/2206.13304 · HTML: https://mlsanity.com/paper/2206.13304/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 27 Jun 2022.

## Builds on (most cited first, 25 of 25)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [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)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Generating Visual Explanations](https://mlsanity.com/paper/1603.08507/) (2016)
- [A Large-Scale Car Dataset for Fine-Grained Categorization and Verification](https://mlsanity.com/paper/1506.08959/) (2015)
- [Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning](https://mlsanity.com/paper/1912.10389/) (2019)
- [Attention Branch Network: Learning of Attention Mechanism for Visual Explanation](https://mlsanity.com/paper/1812.10025/) (2018)
- [Learning to Navigate for Fine-grained Classification](https://mlsanity.com/paper/1809.00287/) (2018)
- [The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification](https://mlsanity.com/paper/1411.6447/) (2014)
- [Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up](https://mlsanity.com/paper/1903.02827/) (2019)
- [Object-Part Attention Model for Fine-grained Image Classification](https://mlsanity.com/paper/1704.01740/) (2017)
- [Bird Species Categorization Using Pose Normalized Deep Convolutional Nets](https://mlsanity.com/paper/1406.2952/) (2014)
- [Attribute Recognition by Joint Recurrent Learning of Context and Correlation](https://mlsanity.com/paper/1709.08553/) (2017)
- [Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks](https://mlsanity.com/paper/1504.08289/) (2015)
- [Attribute-Aware Attention Model for Fine-grained Representation Learning](https://mlsanity.com/paper/1901.00392/) (2019)
- [Multi-task CNN Model for Attribute Prediction](https://mlsanity.com/paper/1601.00400/) (2016)
- [Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition](https://mlsanity.com/paper/2004.02684/) (2020)
- [Classification-Specific Parts for Improving Fine-Grained Visual Categorization](https://mlsanity.com/paper/1909.07075/) (2019)
- [Recognizing Part Attributes with Insufficient Data](https://mlsanity.com/paper/1908.03335/) (2019)
- [Unsupervised Part Mining for Fine-grained Image Classification](https://mlsanity.com/paper/1902.09941/) (2019)
- [Unsupervised part learning for visual recognition](https://mlsanity.com/paper/1704.03755/) (2017)
- [Human-Understandable Decision Making for Visual Recognition](https://mlsanity.com/paper/2103.03429/) (2021)

## Built on by (most cited first, 6 of 6)

- [Natural Example-Based Explainability: a Survey](https://mlsanity.com/paper/2309.03234/) (2023)
- [PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers](https://mlsanity.com/paper/2407.04538/) (2024)
- [Transparent Anomaly Detection via Concept-based Explanations](https://mlsanity.com/paper/2310.10702/) (2023)
- [Evaluation of Explanation Methods of AI -- CNNs in Image Classification Tasks with Reference-based and No-reference Metrics](https://mlsanity.com/paper/2212.01222/) (2022)
- [Interpretable Out-Of-Distribution Detection Using Pattern Identification](https://mlsanity.com/paper/2302.10303/) (2023)
- [Contextualised Out-of-Distribution Detection using Pattern Identication](https://mlsanity.com/paper/2311.12855/) (2023)

## Abstract (arXiv)

In this paper, we present PARTICUL, a novel algorithm for unsupervised learning of part detectors from datasets used in fine-grained recognition. It exploits the macro-similarities of all images in the training set in order to mine for recurring patterns in the feature space of a pre-trained convolutional neural network. We propose new objective functions enforcing the locality and unicity of the detected parts. Additionally, we embed our detectors with a confidence measure based on correlation scores, allowing the system to estimate the visibility of each part. We apply our method on two public fine-grained datasets (Caltech-UCSD Bird 200 and Stanford Cars) and show that our detectors can consistently highlight parts of the object while providing a good measure of the confidence in their prediction. We also demonstrate that these detectors can be directly used to build part-based fine-grained classifiers that provide a good compromise between the transparency of prototype-based approaches and the performance of non-interpretable methods.