• Publications
  • Influence
Learning to Compare: Relation Network for Few-Shot Learning
TLDR
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. Expand
Deep Mutual Learning
TLDR
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. Expand
Person re-identification by probabilistic relative distance comparison
TLDR
A novel Probabilistic Relative Distance Comparison (PRDC) model is introduced, which differs from most existing distance learning methods in that it aims to maximise the probability of a pair of true match having a smaller distance than that of a wrong match pair, which makes the model more tolerant to appearance changes and less susceptible to model over-fitting. Expand
Semantic Autoencoder for Zero-Shot Learning
TLDR
This work presents a novel solution to ZSL based on learning a Semantic AutoEncoder (SAE), which outperforms significantly the existing ZSL models with the additional benefit of lower computational cost and beats the state-of-the-art when the SAE is applied to supervised clustering problem. Expand
Reidentification by Relative Distance Comparison
  • W. Zheng, S. Gong, T. Xiang
  • Mathematics, Computer Science
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 March 2013
TLDR
This paper formulate person reidentification as a relative distance comparison (RDC) learning problem in order to learn the optimal similarity measure between a pair of person images and develops an ensemble RDC model. Expand
Learning a Deep Embedding Model for Zero-Shot Learning
  • Li Zhang, T. Xiang, S. Gong
  • Computer Science, Mathematics
  • IEEE Conference on Computer Vision and Pattern…
  • 15 November 2016
TLDR
This paper proposes to use the visual space as the embedding space instead of embedding into a semantic space or an intermediate space, and argues that in this space, the subsequent nearest neighbour search would suffer much less from the hubness problem and thus become more effective. Expand
Learning a Discriminative Null Space for Person Re-identification
  • Li Zhang, T. Xiang, S. Gong
  • Computer Science, Mathematics
  • IEEE Conference on Computer Vision and Pattern…
  • 7 March 2016
TLDR
This work proposes to overcome the SSS problem in re-id distance metric learning by matching people in a discriminative null space of the training data, which has a fixed dimension, a closed-form solution and is very efficient to compute. Expand
Person Re-Identification by Support Vector Ranking
TLDR
This work converts the person re-identification problem from an absolute scoring p roblem to a relative ranking problem and develops an novel Ensemble RankSVM to overcome the scalability limitation problem suffered by existing SVM-based ranking methods. Expand
Associating Groups of People
TLDR
A novel people group representation and a group matching algorithm are proposed that addresses changes in the relative positions of people in a group and the latter deals with variations in illumination and viewpoint across camera views. Expand
Unsupervised Cross-Dataset Transfer Learning for Person Re-identification
TLDR
This work presents an multi-task dictionary learning method which is able to learn a dataset-shared but target-data-biased representation, and demonstrates that the method significantly outperforms the state-of-the-art. Expand
...
1
2
3
4
5
...