# Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks

arXiv: https://arxiv.org/abs/1504.08289 · HTML: https://mlsanity.com/paper/1504.08289/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2015.

## Built on by (most cited first, 22 of 22)

- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [Unsupervised Part Discovery from Contrastive Reconstruction](https://mlsanity.com/paper/2111.06349/) (2021)
- [Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification](https://mlsanity.com/paper/2101.06635/) (2021)
- [Learning Gabor Texture Features for Fine-Grained Recognition](https://mlsanity.com/paper/2308.05396/) (2023)
- [SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval](https://mlsanity.com/paper/2209.13833/) (2022)
- [Exploring Localization for Self-supervised Fine-grained Contrastive Learning](https://mlsanity.com/paper/2106.15788/) (2021)
- [The Curious Layperson: Fine-Grained Image Recognition without Expert Labels](https://mlsanity.com/paper/2111.03651/) (2021)
- [Part-guided Relational Transformers for Fine-grained Visual Recognition](https://mlsanity.com/paper/2212.13685/) (2022)
- [Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace](https://mlsanity.com/paper/2305.15775/) (2023)
- [PARTICUL: Part Identification with Confidence measure using Unsupervised Learning](https://mlsanity.com/paper/2206.13304/) (2022)
- [Deep Learning Pipeline for Automated Visual Moth Monitoring: Insect Localization and Species Classification](https://mlsanity.com/paper/2307.15427/) (2023)
- [PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognition](https://mlsanity.com/paper/2309.13822/) (2023)
- [Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification](https://mlsanity.com/paper/2106.03432/) (2021)
- [DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image Detection](https://mlsanity.com/paper/2203.09121/) (2022)
- [Test-Time Adaptation for Super-Resolution: You Only Need to Overfit on a Few More Images](https://mlsanity.com/paper/2104.02663/) (2021)
- [Parsing Objects at a Finer Granularity: A Survey](https://mlsanity.com/paper/2212.13693/) (2022)
- [ODMTCNet: An Interpretable Multi-view Deep Neural Network Architecture for Image Feature Representation](https://mlsanity.com/paper/2110.14830/) (2021)
- [Sequential Random Network for Fine-grained Image Classification](https://mlsanity.com/paper/2103.07230/) (2021)
- [An attention-driven hierarchical multi-scale representation for visual recognition](https://mlsanity.com/paper/2110.12178/) (2021)
- [ELFIS: Expert Learning for Fine-grained Image Recognition Using Subsets](https://mlsanity.com/paper/2303.09269/) (2023)
- [Channel-Wise Contrastive Learning for Learning with Noisy Labels](https://mlsanity.com/paper/2308.06952/) (2023)

## Abstract (arXiv)

Part models of object categories are essential for challenging recognition tasks, where differences in categories are subtle and only reflected in appearances of small parts of the object. We present an approach that is able to learn part models in a completely unsupervised manner, without part annotations and even without given bounding boxes during learning. The key idea is to find constellations of neural activation patterns computed using convolutional neural networks. In our experiments, we outperform existing approaches for fine-grained recognition on the CUB200-2011, NA birds, Oxford PETS, and Oxford Flowers dataset in case no part or bounding box annotations are available and achieve state-of-the-art performance for the Stanford Dog dataset. We also show the benefits of neural constellation models as a data augmentation technique for fine-tuning. Furthermore, our paper unites the areas of generic and fine-grained classification, since our approach is suitable for both scenarios. The source code of our method is available online at http://www.inf-cv.uni-jena.de/part_discovery