Deep Image Category Discovery using a Transferred Similarity Function
By Yen-Chang Hsu, Zhaoyang Lv, Zsolt Kira. 2016
15 citations recorded by the source corpus.
Automatically discovering image categories in unlabeled natural images is one of the important goals of unsupervised learning. However, the task is challenging and even human beings define visual categories based on a large amount of prior knowledge. In this paper, we similarly utilize prior knowledge to facilitate the discovery of image categories. We present a novel end-to-end network to map unlabeled images to categories as a clustering network. We propose that this network can be learned with contrastive loss which is only based on weak binary pair-wise constraints. Such binary constraints can be learned from datasets in other domains as transferred similarity functions, which mimic a simple knowledge transfer. We first evaluate our experiments on the MNIST dataset as a proof of concept, based on predicted similarities trained on Omniglot, showing a 99\% accuracy which significantly outperforms clustering based approaches. Then we evaluate the discovery performance on Cifar-10, STL-10, and ImageNet, which achieves both state-of-the-art accuracy and shows it can be scalable to various large natural images.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Andrew Zisserman
- Andrea Vedaldi
- Dacheng Tao
- Trevor Darrell
- Jitendra Malik
- Ming-Hsuan Yang
- Xiaogang Wang
Citations in the corpus
- Grafit: Learning fine-grained image representations with coarse labels (2020, background): “Note that this work departs from the popular framework of object/category discovery [11, 21, 32, 57, 58], which is completely unsupervised.”
- Unseen Class Discovery in Open-world Classification (2018, background): “Hsu et al. (2016) proposed a deep clustering network that can be transferred to a different domain.”
- Automatically Discovering and Learning New Visual Categories with Ranking Statistics (2020, methodology): “In both, a similarity prediction network (SPN), also used in (Hsu et al., 2016), is first trained on a labelled dataset.”