Search Results for author:
Found 71 papers, 35 papers with code
A Tree-Structured Decoder for Image-to-Markup Generation
Recent encoder-decoder approaches typically employ string decoders to convert images into serialized strings for image-to-markup.
Region Proposal Network Pre-Training Helps Label-Efficient Object Detection
In this work, we propose a simple pretext task that provides an effective pre-training for the RPN, towards efficiently improving downstream object detection performance.
ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization
We evaluate our paradigm on a diverse model zoo consisting of 35 models for various OoD tasks and demonstrate: (i) model ranking is better correlated with fine-tuning ranking than previous methods and up to 9859x faster than brute-force fine-tuning; (ii) OoD generalization after model ensemble with feature selection outperforms the state-of-the-art methods and the accuracy on most challenging task DomainNet is improved from 46. 5\% to 50. 6\%.
MEDFAIR: Benchmarking Fairness for Medical Imaging
In this work, we introduce MEDFAIR, a framework to benchmark the fairness of machine learning models for medical imaging.
Towards 3D VR-Sketch to 3D Shape Retrieval
In this paper, we offer a different perspective towards answering these questions -- we study the use of 3D sketches as an input modality and advocate a VR-scenario where retrieval is conducted.
Fine-Grained VR Sketching: Dataset and Insights
We then, for the first time, study the scenario of fine-grained 3D VR sketch to 3D shape retrieval, as a novel VR sketching application and a proving ground to drive out generic insights to inform future research.
Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection
Out-of-distribution (OOD) detection has recently received much attention from the machine learning community due to its importance in deploying machine learning models in real-world applications.
Long-tail Recognition via Compositional Knowledge Transfer
In this work, we introduce a novel strategy for long-tail recognition that addresses the tail classes' few-shot problem via training-free knowledge transfer.
Domain Attention Consistency for Multi-Source Domain Adaptation
Importantly, the attention module is supervised by a consistency loss, which is imposed on the distributions of channel attention weights between source and target domains.
Loss Function Learning for Domain Generalization by Implicit Gradient
We take a different approach, and explore the impact of the ERM loss function on out-of-domain generalisation.
Residual Contrastive Learning: Unsupervised Representation Learning from Residuals
In the era of deep learning, supervised residual learning (ResL) has led to many breakthroughs in low-level vision such as image restoration and enhancement tasks.
SketchODE: Learning neural sketch representation in continuous time
Learning meaningful representations for chirographic drawing data such as sketches, handwriting, and flowcharts is a gateway for understanding and emulating human creative expression.
MixStyle Neural Networks for Domain Generalization and Adaptation
In this work, we address domain generalization with MixStyle, a plug-and-play, parameter-free module that is simply inserted to shallow CNN layers and requires no modification to training objectives.
EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization
Gradient-based meta-learning and hyperparameter optimization have seen significant progress recently, enabling practical end-to-end training of neural networks together with many hyperparameters.
Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images
We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), and derive an unsupervised visual representation learning framework, suitable for low-level vision tasks with noisy inputs.
Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error
The problem is especially noticeable when using modern neural networks, for which there is a significant difference between the confidence of the model and the probability of correct prediction.
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.
Domain Generalization with MixStyle
Our method, termed MixStyle, is motivated by the observation that visual domain is closely related to image style (e. g., photo vs.~sketch images).
Ranked #43 on
Domain Generalization
on PACS
Pinpointing the Memory Behaviors of DNN Training
The training of deep neural networks (DNNs) is usually memory-hungry due to the limited device memory capacity of DNN accelerators.
Cloud2Curve: Generation and Vectorization of Parametric Sketches
Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations.
StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval
With this meta-learning framework, our model can not only disentangle the cross-modal shared semantic content for SBIR, but can adapt the disentanglement to any unseen user style as well, making the SBIR model truly style-agnostic.
More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval
A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack of sketch-photo pairs.
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.
Context-Aware Layout to Image Generation with Enhanced Object Appearance
We argue that these are caused by the lack of context-aware object and stuff feature encoding in their generators, and location-sensitive appearance representation in their discriminators.
Ranked #1 on
Layout-to-Image Generation
on COCO-Stuff 128x128
Tensor Composition Net for Visual Relationship Prediction
We present a novel Tensor Composition Net (TCN) to predict visual relationships in images.
Cross-Modal Hierarchical Modelling for Fine-Grained Sketch Based Image Retrieval
In this paper, we study a further trait of sketches that has been overlooked to date, that is, they are hierarchical in terms of the levels of detail -- a person typically sketches up to various extents of detail to depict an object.
Learning to Generate Novel Domains for Domain Generalization
This explicitly increases the diversity of available training domains and leads to a more generalizable model.
Ranked #51 on
Domain Generalization
on PACS
BézierSketch: A generative model for scalable vector sketches
The study of neural generative models of human sketches is a fascinating contemporary modeling problem due to the links between sketch image generation and the human drawing process.
Flexible Dataset Distillation: Learn Labels Instead of Images
In particular, we study the problem of label distillation - creating synthetic labels for a small set of real images, and show it to be more effective than the prior image-based approach to dataset distillation.
Augmented Sliced Wasserstein Distances
While theoretically appealing, the application of the Wasserstein distance to large-scale machine learning problems has been hampered by its prohibitive computational cost.
Sequential Learning for Domain Generalization
In DG this means encountering a sequence of domains and at each step training to maximise performance on the next domain.
Ranked #62 on
Domain Generalization
on PACS
Domain Adaptive Ensemble Learning
Each such classifier is an expert to its own domain and a non-expert to others.
Deep Domain-Adversarial Image Generation for Domain Generalisation
This is achieved by having a learning objective formulated to ensure that the generated data can be correctly classified by the label classifier while fooling the domain classifier.
Ranked #49 on
Domain Generalization
on PACS
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.
DADA: Differentiable Automatic Data Augmentation
In this paper, we propose Differentiable Automatic Data Augmentation (DADA) which dramatically reduces the cost.
Ranked #13 on
Data Augmentation
on ImageNet
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
+1
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.
Learning Generalisable Omni-Scale Representations for Person Re-Identification
An effective person re-identification (re-ID) model should learn feature representations that are both discriminative, for distinguishing similar-looking people, and generalisable, for deployment across datasets without any adaptation.
Unsupervised Domain Adaptation
Unsupervised Person Re-Identification
Simple and Effective Stochastic Neural Networks
Stochastic neural networks (SNNs) are currently topical, with several paradigms being actively investigated including dropout, Bayesian neural networks, variational information bottleneck (VIB) and noise regularized learning.
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.
Omni-Scale Feature Learning for Person Re-Identification
As an instance-level recognition problem, person re-identification (ReID) relies on discriminative features, which not only capture different spatial scales but also encapsulate an arbitrary combination of multiple scales.
Ranked #2 on
Person Re-Identification
on MSMT17-C
Incorporating prior financial domain knowledge into neural networks for implied volatility surface prediction
This is one of the very first studies which discuss a methodological framework that incorporates prior financial domain knowledge into neural network architecture design and model training.
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 #97 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 #62 on
Domain Generalization
on PACS
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 #19 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.
Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental States
To advance subtle expression recognition, we contribute a Large-scale Subtle Emotions and Mental States in the Wild database (LSEMSW).
Deep Neural Decision Trees
In this work, we present Deep Neural Decision Trees (DNDT) -- tree models realised by neural networks.
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).
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.
Learning to Generalize: Meta-Learning for Domain Generalization
We propose a novel {meta-learning} method for domain generalization.
Ranked #100 on
Domain Generalization
on PACS
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 #103 on
Domain Generalization
on PACS
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.
Weakly Supervised Image Annotation and Segmentation with Objects and Attributes
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.
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.
Learning to Learn: Meta-Critic Networks for Sample Efficient Learning
We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples.
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).
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.
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.
Deep Multi-task Representation Learning: A Tensor Factorisation Approach
Our approach applies to both homogeneous and heterogeneous MTL.
Frankenstein: Learning Deep Face Representations using Small Data
To train such networks, very large training sets are needed with millions of labeled images.
Zero-Shot Domain Adaptation via Kernel Regression on the Grassmannian
Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing.
When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition
In this work, we conduct an extensive evaluation of CNN-based face recognition systems (CNN-FRS) on a common ground to make our work easily reproducible.
Weakly Supervised Learning of Objects, Attributes and their Associations
When humans describe images they tend to use combinations of nouns and adjectives, corresponding to objects and their associated attributes respectively.
Transductive Multi-class and Multi-label Zero-shot Learning
Recently, zero-shot learning (ZSL) has received increasing interest.
Transductive Multi-label Zero-shot Learning
Zero-shot learning has received increasing interest as a means to alleviate the often prohibitive expense of annotating training data for large scale recognition problems.
Sketch-a-Net that Beats Humans
We propose a multi-scale multi-channel deep neural network framework that, for the first time, yields sketch recognition performance surpassing that of humans.
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).
