Log In Sign Up

Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks

by   Marcel Simon, et al.

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


page 3

page 6


The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition

Current approaches for fine-grained recognition do the following: First,...

Part Detector Discovery in Deep Convolutional Neural Networks

Current fine-grained classification approaches often rely on a robust lo...

Iterative Object and Part Transfer for Fine-Grained Recognition

The aim of fine-grained recognition is to identify sub-ordinate categori...

WikiChurches: A Fine-Grained Dataset of Architectural Styles with Real-World Challenges

We introduce a novel dataset for architectural style classification, con...

Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization

We present a simple deep learning framework to simultaneously predict ke...

Cascade one-vs-rest detection network for fine-grained recognition without part annotations

Fine-grained recognition is a challenging task due to the small intra-ca...

End-to-end Learning of a Fisher Vector Encoding for Part Features in Fine-grained Recognition

Part-based approaches for fine-grained recognition do not show the expec...