Published on Tue Jun 29 2021

AutoNovel: Automatically Discovering and Learning Novel Visual Categories

Kai Han, Sylvestre-Alvise Rebuffi, Sébastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman

We tackle the problem of discovering novel classes in an image collection. We use self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data. We evaluate AutoNovel on standard classification benchmarks and show that it outperforms current methods for novel category discovery.

1
10
51
Abstract

We tackle the problem of discovering novel classes in an image collection given labelled examples of other classes. We present a new approach called AutoNovel to address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labelled 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; (2) we use ranking statistics to transfer the model's knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data. Moreover, we propose a method to estimate the number of classes for the case where the number of new categories is not known a priori. We evaluate AutoNovel on standard classification benchmarks and substantially outperform current methods for novel category discovery. In addition, we also show that AutoNovel can be used for fully unsupervised image clustering, achieving promising results.

Thu Feb 13 2020
Computer Vision
Automatically Discovering and Learning New Visual Categories with Ranking Statistics
We tackle the problem of discovering novel classes in an image collection given labelled examples of other classes. The challenge is to leverage the information contained in the labelled images in order to learn ageneral-purpose clustering model.
0
0
0
Mon Feb 10 2020
Machine Learning
Semi-Supervised Class Discovery
Systems that generate labels can be deployed against an arbitrary amount of data. We show that our class discovery system can be successfully applied to vision and language. We demonstrate the value of semi-supervised learning in automatically discovering novel classes.
0
0
0
Mon Aug 26 2019
Computer Vision
Learning to Discover Novel Visual Categories via Deep Transfer Clustering
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 ambiguity of clustering, and improve the quality of the newly discovered Classes.
0
0
0
Mon Feb 15 2021
Machine Learning
One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes
Prototype generation methods aim to create a small set of synthetic observations that accurately represent a training dataset but greatly reduce the computational cost of learning from it. Assigning soft labels to prototypes can allow increasingly small sets of prototypes to accurately represent the original training dataset.
0
0
0
Tue Feb 02 2016
Computer Vision
Unsupervised High-level Feature Learning by Ensemble Projection for Semi-supervised Image Classification and Image Clustering
The method is dubbed Ensemble Projection (EP) EP captures not only the characteristics of individual images, but also the relationships among images. It is conceptually simple and computationally efficient, yet effective and flexible.
0
0
0
Sat Feb 06 2021
Machine Learning
Open-World Semi-Supervised Learning
0
0
0
Wed Mar 21 2018
Computer Vision
Unsupervised Representation Learning by Predicting Image Rotations
Deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. In order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale. We propose to learn image features by training ConvNets to recognize the 2d rotation that
1
7
53
Thu Sep 04 2014
Computer Vision
Very Deep Convolutional Networks for Large-Scale Image Recognition
Convolutional networks of increasing depth can achieve state-of-the-art results. The research was the basis of the team's ImageNet Challenge 2014.
2
2
7
Mon Aug 06 2018
Machine Learning
A Survey on Deep Transfer Learning
Deep learning has recently received increasing attention from researchers. In some domains, like bioinformatics and robotics, it is very difficult to construct a large-scale well-annotated dataset.
1
1
1
Tue Jul 17 2018
Computer Vision
Invariant Information Clustering for Unsupervised Image Classification and Segmentation
The method is not specialised to computer vision and operates on any paired dataset samples. The trained network directly outputs semantic labels, rather than high dimensional representations that need external processing. The objective is simply to maximise mutual information between the class assignments of each pair.
1
0
1
Mon Dec 22 2014
Machine Learning
Adam: A Method for Stochastic Optimization
Adam is an algorithm for first-order gradient-based optimization of stochastic objective functions. The method is straightforward to implement and has little memory requirements. It is well suited for problems that are large in terms of data and parameters.
3
0
1
Thu Feb 28 2019
Computer Vision
Efficient Parameter-free Clustering Using First Neighbor Relations
We present a new clustering method in the form of a single clustering equation that is able to directly discover groupings in the data. The proposed algorithm belongs to the family of hierarchical hierarchical methods. The technique has a very low computational overhead, is scalable and applicable to large practical problems.
0
0
0