Search Results for author:
Found 75 papers, 25 papers with code
A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning
We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning, including hyperparameter optimization, loss function learning, few-shot learning, invariance learning and more.
Better Practices for Domain Adaptation
However, the domain shift scenario raises a second more subtle challenge: the difficulty of performing hyperparameter optimisation (HPO) for these adaptation algorithms without access to a labelled validation set.
Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics
Deep learning-based recognition systems are deployed at scale for several real-world applications that inevitably involve our social life.
Accelerating Self-Supervised Learning via Efficient Training Strategies
Recently the focus of the computer vision community has shifted from expensive supervised learning towards self-supervised learning of visual representations.
Fisher SAM: Information Geometry and Sharpness Aware Minimisation
Recent sharpness-aware minimisation (SAM) is known to find flat minima which is beneficial for better generalisation with improved robustness.
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
To this end, we explore few-shot learning from the perspective of neural network architecture, as well as a three stage pipeline of network updates under different data supplies, where unsupervised external data is considered for pre-training, base categories are used to simulate few-shot tasks for meta-training, and the scarcely labelled data of an novel task is taken for fine-tuning.
Ranked #2 on
Few-Shot Image Classification
on Meta-Dataset
Meta Mirror Descent: Optimiser Learning for Fast Convergence
The resulting framework, termed Meta Mirror Descent (MetaMD), learns to accelerate optimisation speed.
Why Do Self-Supervised Models Transfer? Investigating the Impact of Invariance on Downstream Tasks
We show that learned invariances strongly affect downstream task performance and confirm that different downstream tasks benefit from polar opposite (in)variances, leading to performance loss when the standard augmentation strategy is used.
Self-Supervised Representation Learning: Introduction, Advances and Challenges
Self-supervised representation learning methods aim to provide powerful deep feature learning without the requirement of large annotated datasets, thus alleviating the annotation bottleneck that is one of the main barriers to practical deployment of deep learning today.
Towards Unsupervised Sketch-based Image Retrieval
The practical value of existing supervised sketch-based image retrieval (SBIR) algorithms is largely limited by the requirement for intensive data collection and labeling.
Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting
This data is uniquely characterised by its existence in dual modalities of rasterized images and vector coordinate sequences.
Searching for Robustness: Loss Learning for Noisy Classification Tasks
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.
FedH2L: Federated Learning with Model and Statistical Heterogeneity
Federated learning (FL) enables distributed participants to collectively learn a strong global model without sacrificing their individual data privacy.
A Simple Feature Augmentation for Domain Generalization
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.
Tensor Composition Net for Visual Relationship Prediction
We present a novel Tensor Composition Net (TCN) to predict visual relationships in images.
How Well Do Self-Supervised Models Transfer?
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.
On Learning Semantic Representations for Million-Scale Free-Hand Sketches
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.
Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights
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.
Online Meta-Critic Learning for Off-Policy Actor-Critic Methods
Off-Policy Actor-Critic (Off-PAC) methods have proven successful in a variety of continuous control tasks.
Unlimited Resolution Image Generation with R2D2-GANs
In this paper we present a novel simulation technique for generating high quality images of any predefined resolution.
Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval
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
+2
Fine-Grained Instance-Level Sketch-Based Video Retrieval
Existing sketch-analysis work studies sketches depicting static objects or scenes.
Distance-Based Regularisation of Deep Networks for Fine-Tuning
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.
Deep Learning for Free-Hand Sketch: A Survey
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
Existing Lipschitz-based provable defences to adversarial examples only cover the L2 threat model.
Index Tracking with Cardinality Constraints: A Stochastic Neural Networks Approach
Compared with the benchmarked models, our model has the lowest tracking error, across a range of portfolio sizes.
Deep clustering with concrete k-means
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.
Ranked #2 on
Online Clustering
on cifar10
Goal-Driven Sequential Data Abstraction
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.
Measuring the Transferability of Adversarial Examples
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
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.
Investigating Generalisation in Continuous Deep Reinforcement Learning
Deep Reinforcement Learning has shown great success in a variety of control tasks.
Feature-Critic Networks for Heterogeneous Domain Generalization
The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training.
Ranked #121 on
Domain Generalization
on PACS
Episodic Training for Domain Generalization
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.
Ranked #85 on
Domain Generalization
on PACS
TuckER: Tensor Factorization for Knowledge Graph Completion
Knowledge graphs are structured representations of real world facts.
Ranked #9 on
Link Prediction
on FB15k
Disjoint Label Space Transfer Learning with Common Factorised Space
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.
Ranked #21 on
Unsupervised Domain Adaptation
on Market to Duke
RelationNet2: Deep Comparison Columns for Few-Shot Learning
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.
Diversity and Sparsity: A New Perspective on Index Tracking
We introduce the first index tracking method that explicitly optimises both diversity and sparsity in a single joint framework.
Hypernetwork Knowledge Graph Embeddings
Knowledge graphs are graphical representations of large databases of facts, which typically suffer from incompleteness.
Ranked #10 on
Link Prediction
on WN18
Deep Factorised Inverse-Sketching
Instead there is a fundamental process of abstraction and iconic rendering, where overall geometry is warped and salient details are selectively included.
Deep Neural Decision Trees
In this work, we present Deep Neural Decision Trees (DNDT) -- tree models realised by neural networks.
Sketch-a-Classifier: Sketch-based Photo Classifier Generation
Contemporary deep learning techniques have made image recognition a reasonably reliable technology.
Learning Deep Sketch Abstraction
Human free-hand sketches have been studied in various contexts including sketch recognition, synthesis and fine-grained sketch-based image retrieval (FG-SBIR).
SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval
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.
Multi-Level Factorisation Net for Person Re-Identification
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.
Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool
The iVQA task is to generate a question that corresponds to a given image and answer pair.
The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
Many vision problems require matching images of object instances across different domains.
Learning to Compare: Relation Network for Few-Shot Learning
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.
Deep Matching Autoencoders
In this paper we introduce Deep Matching Autoencoders (DMAE), which learn a common latent space and pairing from unpaired multi-modal data.
Learning to Generalize: Meta-Learning for Domain Generalization
We propose a novel {meta-learning} method for domain generalization.
Ranked #124 on
Domain Generalization
on PACS
iVQA: Inverse Visual Question Answering
The iVQA task is to generate a question that corresponds to a given image and answer pair.
Deeper, Broader and Artier Domain Generalization
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.
Ranked #127 on
Domain Generalization
on PACS
Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval
Human sketches are unique in being able to capture both the spatial topology of a visual object, as well as its subtle appearance details.
Ranked #2 on
Sketch-Based Image Retrieval
on Handbags
Attribute-Enhanced Face Recognition With Neural Tensor Fusion Networks
To solve this problem, we establish a theoretical equivalence between tensor optimisation and a two-stream gated neural network.
Scalable and Effective Deep CCA via Soft Decorrelation
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
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.
Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images
We address the problem of localisation of objects as bounding boxes in images and videos with weak labels.
Transferring a Semantic Representation for Person Re-Identification and Search
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.
Deep Mutual Learning
Model distillation is an effective and widely used technique to transfer knowledge from a teacher to a student network.
Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation
(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
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).
Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation
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.
Ranked #7 on
Zero-Shot Action Recognition
on Olympics
Semantic Regularisation for Recurrent Image Annotation
We propose a simple modification to the design pattern that makes learning more effective and efficient.
Gated Neural Networks for Option Pricing: Rationality by Design
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
We propose a framework for training multiple neural networks simultaneously.
ForgetMeNot: Memory-Aware Forensic Facial Sketch Matching
Based on this database we build a model to reverse the forgetting process.
Sketch Me That Shoe
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.
Ranked #3 on
Sketch-Based Image Retrieval
on Chairs
Multivariate Regression on the Grassmannian for Predicting Novel Domains
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.
Transductive Multi-class and Multi-label Zero-shot Learning
Recently, zero-shot learning (ZSL) has received increasing interest.
Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels
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.
Transductive Multi-view Zero-Shot Learning
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.
A Unified Perspective on Multi-Domain and Multi-Task Learning
In this paper, we provide a new neural-network based perspective on multi-task learning (MTL) and multi-domain learning (MDL).
