paper-with-me

홈 › Papers

CNN features are also great at unsupervised classification

2017-07-06 · Joris Guérin, Olivier Gibaru, Stéphane Thiery, Eric Nyiri

This paper aims at providing insight on the transferability of deep CNN features to unsupervised problems. We study the impact of different pretrained CNN feature extractors on the problem of image set clustering for object classification as well as fine-grained classification. We propose a rather straightforward pipeline combining deep-feature extraction using a CNN pretrained on ImageNet and a classic clustering algorithm to classify sets of images. This approach is compared to state-of-the-art algorithms in image-clustering and provides better results. These results strengthen the belief that supervised training of deep CNN on large datasets, with a large variability of classes, extracts better features than most carefully designed engineering approaches, even for unsupervised tasks. We also validate our approach on a robotic application, consisting in sorting and storing objects smartly based on clustering.

📄 PDF Abstract BibTeX arXiv:1707.01700

Code (2)

jorisguerin/pretrainedCNN_clustering 공식 구현
MrGrayCode/Clustering-CNN-Features

Tasks

ClassificationClusteringGeneral ClassificationImage Clustering

Similar Papers 제목 키워드 기반

Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks

2016-06-02 · Boris Knyazev, Erhardt Barth, Thomas Martinetz

In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently. We show that the recursive autoconvolution operator, adop…

ClassificationGeneral Classificationimage-classificationImage Classification

Two stages domain invariant representation learners solve the large co-variate shift in unsupervised domain adaptation with two dimensional data domains

2024-12-06 · Hisashi Oshima, Tsuyoshi Ishizone, Tomoyuki Higuchi

Recent developments in the unsupervised domain adaptation (UDA) enable the unsupervised machine learning (ML) prediction for target data, thus this will accelerate real world applications with ML models such as image rec…

Domain AdaptationRepresentation LearningUnsupervised Domain Adaptation

Contrastive Psudo-supervised Classification for Intra-Pulse Modulation of Radar Emitter Signals Using data augmentation

2022-10-13 · HanCong Feng, XinHai Yan, Kaili Jiang, Xinyu Zhao 외

The automatic classification of radar waveform is a fundamental technique in electronic countermeasures (ECM).Recent supervised deep learning-based methods have achieved great success in a such classification task.Howeve…

ClassificationClusteringData AugmentationDeep Learning+1

Tagger: Deep Unsupervised Perceptual Grouping

2016-06-21 · NeurIPS 2016 12 · Klaus Greff, Antti Rasmus, Mathias Berglund, Tele Hotloo Hao 외

We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the group…

General ClassificationSegmentation

Unsupervised Feature Learning for Writer Identification and Writer Retrieval

2017-05-25 · Vincent Christlein, Martin Gropp, Stefan Fiel, Andreas Maier

Deep Convolutional Neural Networks (CNN) have shown great success in supervised classification tasks such as character classification or dating. Deep learning methods typically need a lot of annotated training data, whic…

ClassificationClusteringGeneral ClassificationRetrieval+1