Search Results for author: Timothy M. Hospedales

Found 66 papers, 21 papers with code

Searching for Robustness: Loss Learning for Noisy Classification Tasks

no code implementations ICCV 2021 Boyan Gao, Henry Gouk, Timothy M. Hospedales

We present a "learning to learn" approach for automatically constructing white-box classification loss functions that are robust to label noise in the training data.

Classification General Classification

FedH2L: Federated Learning with Model and Statistical Heterogeneity

no code implementations27 Jan 2021 Yiying Li, Wei Zhou, Huaimin Wang, Haibo Mi, Timothy M. Hospedales

Federated learning (FL) enables distributed participants to collectively learn a strong global model without sacrificing their individual data privacy.

Federated Learning

A Simple Feature Augmentation for Domain Generalization

no code implementations ICCV 2021 Pan Li, Da Li, Wei Li, Shaogang Gong, Yanwei Fu, Timothy M. Hospedales

The topical domain generalization (DG) problem asks trained models to perform well on an unseen target domain with different data statistics from the source training domains.

Data Augmentation Domain Generalization

Tensor Composition Net for Visual Relationship Prediction

no code implementations10 Dec 2020 Yuting Qiang, Yongxin Yang, Yanwen Guo, Timothy M. Hospedales

However Visual Relationship Prediction (VRP) also provides a more challenging test of image understanding than conventional image tagging, and is difficult to learn due to a large label-space and incomplete annotation.

Image Retrieval Multi-Label Classification +1

How Well Do Self-Supervised Models Transfer?

1 code implementation CVPR 2021 Linus Ericsson, Henry Gouk, Timothy M. Hospedales

We evaluate the transfer performance of 13 top self-supervised models on 40 downstream tasks, including many-shot and few-shot recognition, object detection, and dense prediction.

Few-Shot Learning Fine-Grained Image Recognition +5

On Learning Semantic Representations for Million-Scale Free-Hand Sketches

1 code implementation7 Jul 2020 Peng Xu, Yongye Huang, Tongtong Yuan, Tao Xiang, Timothy M. Hospedales, Yi-Zhe Song, Liang Wang

Specifically, we use our dual-branch architecture as a universal representation framework to design two sketch-specific deep models: (i) We propose a deep hashing model for sketch retrieval, where a novel hashing loss is specifically designed to accommodate both the abstract and messy traits of sketches.

Learning Semantic Representations Zero-Shot Learning

Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights

no code implementations22 Jun 2020 Linus Ericsson, Henry Gouk, Timothy M. Hospedales

We show that by learning Bayesian instance weights for the unlabelled data, we can improve the downstream classification accuracy by prioritising the most useful instances.

Meta-Learning Self-Supervised Learning

Unlimited Resolution Image Generation with R2D2-GANs

no code implementations2 Mar 2020 Marija Jegorova, Antti Ilari Karjalainen, Jose Vazquez, Timothy M. Hospedales

In this paper we present a novel simulation technique for generating high quality images of any predefined resolution.

Image Generation

Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval

1 code implementation24 Feb 2020 Ayan Kumar Bhunia, Yongxin Yang, Timothy M. Hospedales, Tao Xiang, Yi-Zhe Song

Fine-grained sketch-based image retrieval (FG-SBIR) addresses the problem of retrieving a particular photo instance given a user's query sketch.

Cross-Modal Retrieval On-the-Fly Sketch Based Image Retrieval

Distance-Based Regularisation of Deep Networks for Fine-Tuning

1 code implementation ICLR 2021 Henry Gouk, Timothy M. Hospedales, Massimiliano Pontil

Our bound is highly relevant for fine-tuning, because providing a network with a good initialisation based on transfer learning means that learning can modify the weights less, and hence achieve tighter generalisation.

Transfer Learning

Deep Learning for Free-Hand Sketch: A Survey and A Toolbox

2 code implementations8 Jan 2020 Peng Xu, Timothy M. Hospedales, Qiyue Yin, Yi-Zhe Song, Tao Xiang, Liang Wang

Free-hand sketches are highly illustrative, and have been widely used by humans to depict objects or stories from ancient times to the present.

Optimising Neural Network Architectures for Provable Adversarial Robustness

no code implementations ICLR 2020 Henry Gouk, Timothy M. Hospedales

Existing Lipschitz-based provable defences to adversarial examples only cover the L2 threat model.

Index Tracking with Cardinality Constraints: A Stochastic Neural Networks Approach

no code implementations12 Nov 2019 Yu Zheng, Bowei Chen, Timothy M. Hospedales, Yongxin Yang

Compared with the benchmarked models, our model has the lowest tracking error, across a range of portfolio sizes.

Deep clustering with concrete k-means

no code implementations17 Oct 2019 Boyan Gao, Yongxin Yang, Henry Gouk, Timothy M. Hospedales

We address the problem of simultaneously learning a k-means clustering and deep feature representation from unlabelled data, which is of interest due to the potential of deep k-means to outperform traditional two-step feature extraction and shallow-clustering strategies.

Deep Clustering

Goal-Driven Sequential Data Abstraction

no code implementations ICCV 2019 Umar Riaz Muhammad, Yongxin Yang, Timothy M. Hospedales, Tao Xiang, Yi-Zhe Song

In the former one asks whether a machine can `understand' enough about the meaning of input data to produce a meaningful but more compact abstraction.

General Reinforcement Learning

Measuring the Transferability of Adversarial Examples

no code implementations14 Jul 2019 Deyan Petrov, Timothy M. Hospedales

Adversarial examples are of wide concern due to their impact on the reliability of contemporary machine learning systems.


Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice

1 code implementation9 May 2019 Jieru Jia, Qiuqi Ruan, Timothy M. Hospedales

Specifically, we observe that the domain discrepancy in \reid{} is due to style and content variance across datasets and demonstrate appropriate Instance and Feature Normalization alleviates much of the resulting domain-shift in Deep \reid{} models.

Person Re-Identification

Feature-Critic Networks for Heterogeneous Domain Generalization

2 code implementations31 Jan 2019 Yiying Li, Yongxin Yang, Wei Zhou, Timothy M. Hospedales

The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training.

Domain Generalization

Episodic Training for Domain Generalization

2 code implementations ICCV 2019 Da Li, Jianshu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, Timothy M. Hospedales

In this paper, we build on this strong baseline by designing an episodic training procedure that trains a single deep network in a way that exposes it to the domain shift that characterises a novel domain at runtime.

Domain Generalization

Disjoint Label Space Transfer Learning with Common Factorised Space

no code implementations6 Dec 2018 Xiaobin Chang, Yongxin Yang, Tao Xiang, Timothy M. Hospedales

In this paper, a unified approach is presented to transfer learning that addresses several source and target domain label-space and annotation assumptions with a single model.

Transfer Learning Unsupervised Domain Adaptation

RelationNet2: Deep Comparison Columns for Few-Shot Learning

1 code implementation17 Nov 2018 Xueting Zhang, Yu-ting Qiang, Flood Sung, Yongxin Yang, Timothy M. Hospedales

We thus propose a new deep comparison network comprised of embedding and relation modules that learn multiple non-linear distance metrics based on different levels of features simultaneously.

Few-Shot Image Classification Metric Learning

Diversity and Sparsity: A New Perspective on Index Tracking

no code implementations6 Sep 2018 Yu Zheng, Timothy M. Hospedales, Yongxin Yang

We introduce the first index tracking method that explicitly optimises both diversity and sparsity in a single joint framework.

Hypernetwork Knowledge Graph Embeddings

2 code implementations21 Aug 2018 Ivana Balažević, Carl Allen, Timothy M. Hospedales

Knowledge graphs are graphical representations of large databases of facts, which typically suffer from incompleteness.

Knowledge Graph Embeddings Knowledge Graphs +1

Deep Factorised Inverse-Sketching

no code implementations ECCV 2018 Kaiyue Pang, Da Li, Jifei Song, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales

Instead there is a fundamental process of abstraction and iconic rendering, where overall geometry is warped and salient details are selectively included.

Sketch-Based Image Retrieval Style Transfer

Deep Neural Decision Trees

5 code implementations19 Jun 2018 Yongxin Yang, Irene Garcia Morillo, Timothy M. Hospedales

In this work, we present Deep Neural Decision Trees (DNDT) -- tree models realised by neural networks.

Learning Deep Sketch Abstraction

no code implementations CVPR 2018 Umar Riaz Muhammad, Yongxin Yang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales

Human free-hand sketches have been studied in various contexts including sketch recognition, synthesis and fine-grained sketch-based image retrieval (FG-SBIR).

Sketch-Based Image Retrieval Sketch Recognition

SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval

1 code implementation CVPR 2018 Peng Xu, Yongye Huang, Tongtong Yuan, Kaiyue Pang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Zhanyu Ma, Jun Guo

Key to our network design is the embedding of unique characteristics of human sketch, where (i) a two-branch CNN-RNN architecture is adapted to explore the temporal ordering of strokes, and (ii) a novel hashing loss is specifically designed to accommodate both the temporal and abstract traits of sketches.

Sketch Recognition

Multi-Level Factorisation Net for Person Re-Identification

no code implementations CVPR 2018 Xiaobin Chang, Timothy M. Hospedales, Tao Xiang

Key to effective person re-identification (Re-ID) is modelling discriminative and view-invariant factors of person appearance at both high and low semantic levels.

Person Re-Identification

Learning to Compare: Relation Network for Few-Shot Learning

9 code implementations CVPR 2018 Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H. S. Torr, Timothy M. Hospedales

Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network.

Few-Shot Image Classification Zero-Shot Learning

Deep Matching Autoencoders

no code implementations16 Nov 2017 Tanmoy Mukherjee, Makoto Yamada, Timothy M. Hospedales

In this paper we introduce Deep Matching Autoencoders (DMAE), which learn a common latent space and pairing from unpaired multi-modal data.

Image Captioning Representation Learning

Deeper, Broader and Artier Domain Generalization

2 code implementations ICCV 2017 Da Li, Yongxin Yang, Yi-Zhe Song, Timothy M. Hospedales

In this paper, we make two main contributions: Firstly, we build upon the favorable domain shift-robust properties of deep learning methods, and develop a low-rank parameterized CNN model for end-to-end DG learning.

Domain Generalization

Weakly Supervised Image Annotation and Segmentation with Objects and Attributes

no code implementations8 Aug 2017 Zhiyuan Shi, Yongxin Yang, Timothy M. Hospedales, Tao Xiang

We propose to model complex visual scenes using a non-parametric Bayesian model learned from weakly labelled images abundant on media sharing sites such as Flickr.

Object Detection Semantic Segmentation

Scalable and Effective Deep CCA via Soft Decorrelation

no code implementations CVPR 2018 Xiaobin Chang, Tao Xiang, Timothy M. Hospedales

Specifically, exact decorrelation is replaced by soft decorrelation via a mini-batch based Stochastic Decorrelation Loss (SDL) to be optimised jointly with the other training objectives.


Actor-Critic Sequence Training for Image Captioning

no code implementations29 Jun 2017 Li Zhang, Flood Sung, Feng Liu, Tao Xiang, Shaogang Gong, Yongxin Yang, Timothy M. Hospedales

Generating natural language descriptions of images is an important capability for a robot or other visual-intelligence driven AI agent that may need to communicate with human users about what it is seeing.

Image Captioning

Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images

no code implementations19 Jun 2017 Zhiyuan Shi, Timothy M. Hospedales, Tao Xiang

We address the problem of localisation of objects as bounding boxes in images and videos with weak labels.

Domain Adaptation Transfer Learning

Transferring a Semantic Representation for Person Re-Identification and Search

no code implementations CVPR 2015 Zhiyuan Shi, Timothy M. Hospedales, Tao Xiang

Learning semantic attributes for person re-identification and description-based person search has gained increasing interest due to attributes' great potential as a pose and view-invariant representation.

Person Re-Identification Person Search

Deep Mutual Learning

7 code implementations CVPR 2018 Ying Zhang, Tao Xiang, Timothy M. Hospedales, Huchuan Lu

Model distillation is an effective and widely used technique to transfer knowledge from a teacher to a student network.

Model distillation Person Re-Identification

Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation

no code implementations9 May 2017 Zhiyuan Shi, Timothy M. Hospedales, Tao Xiang

(3) Our model can be learned with a mixture of weakly labelled and unlabelled data, allowing the large volume of unlabelled images on the Internet to be exploited for learning.

Unifying Multi-Domain Multi-Task Learning: Tensor and Neural Network Perspectives

no code implementations28 Nov 2016 Yongxin Yang, Timothy M. Hospedales

In this chapter, we propose a single framework that unifies multi-domain learning (MDL) and the related but better studied area of multi-task learning (MTL).

Domain Adaptation Multi-Task Learning +1

Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation

no code implementations26 Nov 2016 Xun Xu, Timothy M. Hospedales, Shaogang Gong

In this work, we improve the ability of ZSL to generalise across this domain shift in both model- and data-centric ways by formulating a visual-semantic mapping with better generalisation properties and a dynamic data re-weighting method to prioritise auxiliary data that are relevant to the target classes.

Action Recognition Data Augmentation +1

Gated Neural Networks for Option Pricing: Rationality by Design

1 code implementation14 Sep 2016 Yongxin Yang, Yu Zheng, Timothy M. Hospedales

We propose a neural network approach to price EU call options that significantly outperforms some existing pricing models and comes with guarantees that its predictions are economically reasonable.

Trace Norm Regularised Deep Multi-Task Learning

1 code implementation13 Jun 2016 Yongxin Yang, Timothy M. Hospedales

We propose a framework for training multiple neural networks simultaneously.

Multi-Task Learning

Sketch Me That Shoe

no code implementations CVPR 2016 Qian Yu, Feng Liu, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Chen-Change Loy

We investigate the problem of fine-grained sketch-based image retrieval (SBIR), where free-hand human sketches are used as queries to perform instance-level retrieval of images.

Data Augmentation Sketch-Based Image Retrieval

Multivariate Regression on the Grassmannian for Predicting Novel Domains

no code implementations CVPR 2016 Yongxin Yang, Timothy M. Hospedales

This allows a recognition model to be pre-calibrated for a new domain in advance (e. g., future time or view angle) without waiting for data collection and re-training.

Domain Adaptation

Weakly Supervised Learning of Objects, Attributes and their Associations

no code implementations31 Mar 2015 Zhiyuan Shi, Yongxin Yang, Timothy M. Hospedales, Tao Xiang

When humans describe images they tend to use combinations of nouns and adjectives, corresponding to objects and their associated attributes respectively.

Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels

no code implementations25 Jan 2015 Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Jiechao Xiong, Shaogang Gong, Yizhou Wang, Yuan YAO

In this paper, we propose a more principled way to identify annotation outliers by formulating the subjective visual property prediction task as a unified robust learning to rank problem, tackling both the outlier detection and learning to rank jointly.

Learning-To-Rank Outlier Detection

Transductive Multi-view Zero-Shot Learning

no code implementations19 Jan 2015 Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Shaogang Gong

A projection from a low-level feature space to the semantic representation space is learned from the auxiliary dataset and is applied without adaptation to the target dataset.

Transfer Learning Zero-Shot Learning

A Unified Perspective on Multi-Domain and Multi-Task Learning

no code implementations23 Dec 2014 Yongxin Yang, Timothy M. Hospedales

In this paper, we provide a new neural-network based perspective on multi-task learning (MTL) and multi-domain learning (MDL).

Domain Adaptation Multi-Task Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.