Learning to Compare: Relation Network for Few-Shot Learning
- Flood Sung, Yongxin Yang, Li Zhang, T. Xiang, Philip H. S. Torr, Timothy M. Hospedales
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 16 November 2017
A conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each, which is easily extended to zero- shot learning.
Deeper, Broader and Artier Domain Generalization
- Da Li, Yongxin Yang, Yi-Zhe Song, Timothy M. Hospedales
- Computer ScienceIEEE International Conference on Computer Vision
- 9 October 2017
This paper builds upon the favorable domain shift-robust properties of deep learning methods, and develops a low-rank parameterized CNN model for end-to-end DG learning that outperforms existing DG alternatives.
Deep Mutual Learning
- Ying Zhang, T. Xiang, Timothy M. Hospedales, Huchuan Lu
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 1 June 2017
Surprisingly, it is revealed that no prior powerful teacher network is necessary - mutual learning of a collection of simple student networks works, and moreover outperforms distillation from a more powerful yet static teacher.
TuckER: Tensor Factorization for Knowledge Graph Completion
- Ivana Balazevic, Carl Allen, Timothy M. Hospedales
- Computer ScienceConference on Empirical Methods in Natural…
- 28 January 2019
This work proposes TuckER, a relatively straightforward but powerful linear model based on Tucker decomposition of the binary tensor representation of knowledge graph triples that outperforms previous state-of-the-art models across standard link prediction datasets, acting as a strong baseline for more elaborate models.
Learning to Generalize: Meta-Learning for Domain Generalization
- Da Li, Yongxin Yang, Yi-Zhe Song, Timothy M. Hospedales
- Computer ScienceAAAI Conference on Artificial Intelligence
- 10 October 2017
A novel meta-learning method for domain generalization that trains models with good generalization ability to novel domains and achieves state of the art results on a recent cross-domain image classification benchmark, as well demonstrating its potential on two classic reinforcement learning tasks.
Episodic Training for Domain Generalization
- Da Li, Jian-shu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, Timothy M. Hospedales
- Computer ScienceIEEE International Conference on Computer Vision
- 31 January 2019
Using the Visual Decathlon benchmark, it is demonstrated that the episodic-DG training improves the performance of such a general purpose feature extractor by explicitly training a feature for robustness to novel problems, showing that DG training can benefit standard practice in computer vision.
Multi-relational Poincaré Graph Embeddings
- Ivana Balazevic, Carl Allen, Timothy M. Hospedales
- Computer ScienceNeural Information Processing Systems
- 14 December 2019
The Multi-Relational Poincare model (MuRP) learns relation-specific parameters to transform entity embeddings by Mobius matrix-vector multiplication and Mobius addition and outperform their Euclidean counterpart and existing embedding methods on the link prediction task, particularly at lower dimensionality.
Meta-Learning in Neural Networks: A Survey
- Timothy M. Hospedales, Antreas Antoniou, P. Micaelli, A. Storkey
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 11 April 2020
A new taxonomy is proposed that provides a more comprehensive breakdown of the space of meta-learning methods today and surveys promising applications and successes ofMeta-learning such as few-shot learning and reinforcement learning.
Sketch Me That Shoe
- Qian Yu, Feng Liu, Yi-Zhe Song, T. Xiang, Timothy M. Hospedales, Chen Change Loy
- Computer ScienceComputer Vision and Pattern Recognition
- 12 December 2016
A deep tripletranking model for instance-level SBIR is developed with a novel data augmentation and staged pre-training strategy to alleviate the issue of insufficient fine-grained training data.
Sketch-a-Net that Beats Humans
- Qian Yu, Yongxin Yang, Yi-Zhe Song, T. Xiang, Timothy M. Hospedales
- Computer ScienceBritish Machine Vision Conference
- 30 January 2015
A multi-scale multi-channel deep neural network framework that yields sketch recognition performance surpassing that of humans, and not only delivers the best performance on the largest human sketch dataset to date, but also is small in size making efficient training possible using just CPUs.
...
...