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.
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.
Semantic Autoencoder for Zero-Shot Learning
- Elyor Kodirov, T. Xiang, S. Gong
- Computer ScienceComputer Vision and Pattern Recognition
- 26 April 2017
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.
Person re-identification by probabilistic relative distance comparison
- Weishi Zheng, S. Gong, T. Xiang
- Computer ScienceComputer Vision and Pattern Recognition
- 20 June 2011
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.
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
- Sixiao Zheng, Jiachen Lu, Li Zhang
- Computer ScienceComputer Vision and Pattern Recognition
- 31 December 2020
This paper deploys a pure transformer to encode an image as a sequence of patches, termed SEgmentation TRansformer (SETR), and shows that SETR achieves new state of the art on ADE20K, Pascal Context, and competitive results on Cityscapes.
Learning a Deep Embedding Model for Zero-Shot Learning
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.
Omni-Scale Feature Learning for Person Re-Identification
- Kaiyang Zhou, Yongxin Yang, A. Cavallaro, T. Xiang
- Computer ScienceIEEE International Conference on Computer Vision
- 2 May 2019
A novel deep ReID CNN is designed, termed Omni-Scale Network (OSNet), for omni-scale feature learning by designing a residual block composed of multiple convolutional feature streams, each detecting features at a certain scale.
Reidentification by Relative Distance Comparison
- Weishi Zheng, S. Gong, T. Xiang
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 March 2013
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.
Learning a Discriminative Null Space for Person Re-identification
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.
Person Re-Identification by Support Vector Ranking
- B. J. Prosser, Weishi Zheng, S. Gong, T. Xiang
- Computer ScienceBritish Machine Vision Conference
- 2010
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.
...
...