Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks

2015-04-30 · ICCV 2015 12 · Marcel Simon, Erik Rodner

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

📄 PDF Abstract BibTeX arXiv:1504.08289

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationModel Discovery

Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery

2024-05-27 · Anand Gopalakrishnan, Aleksandar Stanić, Jürgen Schmidhuber, Michael Curtis Mozer

Current state-of-the-art synchrony-based models encode object bindings with complex-valued activations and compute with real-valued weights in feedforward architectures. We argue for the computational advantages of a rec…

Object Object Discovery

Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming

2017-07-20 · Xiu-Shen Wei, Chen-Lin Zhang, Jianxin Wu, Chunhua Shen 외

Reusable model design becomes desirable with the rapid expansion of computer vision and machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, di…

Object object-detection Object Detection Object Discovery+2

Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation

2026-05-23 · Luoyu Chen, Weiqi Wang, Zhiyi Tian, Chenhan Zhang 외 arxiv

Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trigger refusal while preserving…

Part Detector Discovery in Deep Convolutional Neural Networks

2014-11-12 · Marcel Simon, Erik Rodner, Joachim Denzler

Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature representations suitable for discrimination. However, part localization is a challenging tas…

General Classification

Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery

2025-09-02 · Xinrui Gong, Oliver Hahn, Christoph Reich, Krishnakant Singh 외 arxiv

Unsupervised multi-object discovery (MOD) aims to detect and localize distinct object instances in visual scenes without any form of human supervision. Recent approaches leverage object-centric learning (OCL) and motion …

Multi-object discovery Motion Segmentation