Learning to Discover Novel Visual Categories via Deep Transfer Clustering
Kai Han,Andrea Vedaldi,Andrew Zisserman +2 more
- pp 8401-8409
Reads0
Chats0
TLDR
In this article, the authors extend Deep Embedded Clustering to a transfer learning setting and propose a method to estimate the number of classes in the unlabeled data, using knowledge from the known classes.Abstract:
We consider the problem of discovering novel object categories in an image collection. While these images are unlabelled, we also assume prior knowledge of related but different image classes. We use such prior knowledge to reduce the ambiguity of clustering, and improve the quality of the newly discovered classes. Our contributions are twofold. The first contribution is to extend Deep Embedded Clustering to a transfer learning setting; we also improve the algorithm by introducing a representation bottleneck, temporal ensembling, and consistency. The second contribution is a method to estimate the number of classes in the unlabelled data. This also transfers knowledge from the known classes, using them as probes to diagnose different choices for the number of classes in the unlabelled subset. We thoroughly evaluate our method, substantially outperforming state-of-the-art techniques in a large number of benchmarks, including ImageNet, OmniGlot, CIFAR-100, CIFAR-10, and SVHN.read more
Citations
More filters
Posted Content
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
TL;DR: This work proposes GEORGE, a method to both measure and mitigate hidden stratification even when subclass labels are unknown, and theoretically characterize the performance of GEORGE in terms of the worst-case generalization error across any subclass.
Proceedings ArticleDOI
PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering
TL;DR: The method, PiCIE (Pixel-level feature Clustering using Invariance and Equivariance), is the first method capable of segmenting both things and stuff categories without any hyperparameter tuning or task-specific pre-processing.
Posted Content
Automatically Discovering and Learning New Visual Categories with Ranking Statistics
TL;DR: This work suggests that the common approach of bootstrapping an image representation using the labeled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data.
Proceedings ArticleDOI
Neighborhood Contrastive Learning for Novel Class Discovery
TL;DR: In this article, the authors propose to generate hard negatives by mixing labeled and unlabeled samples in the feature space, thus encouraging the model to learn more discriminative representations.
Proceedings ArticleDOI
Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
TL;DR: Zhang et al. as mentioned in this paper proposed to estimate pseudo label similarities between consecutive training generations with clustering consensus and refine pseudo labels with temporally propagated and ensembled pseudo labels.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Some methods for classification and analysis of multivariate observations
TL;DR: The k-means algorithm as mentioned in this paper partitions an N-dimensional population into k sets on the basis of a sample, which is a generalization of the ordinary sample mean, and it is shown to give partitions which are reasonably efficient in the sense of within-class variance.
Journal ArticleDOI
A Survey on Transfer Learning
Sinno Jialin Pan,Qiang Yang +1 more
TL;DR: The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed.