Search Results for author:
Found 47 papers, 17 papers with code
Multimorbidity Content-Based Medical Image Retrieval Using Proxies
Medical imaging data, such as radiology images, are often multimorbidity; a single sample may have more than one pathology present.
A Differentiable Distance Approximation for Fairer Image Classification
We demonstrate that our approach improves the fairness of AI models in varied task and dataset scenarios, whilst still maintaining a high level of classification accuracy.
Deep Laparoscopic Stereo Matching with Transformers
The self-attention mechanism, successfully employed with the transformer structure is shown promise in many computer vision tasks including image recognition, and object detection.
On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation
Inspired by the concept of preconditioning, we propose a novel method to increase adaptation speed for gradient-based meta-learning methods without incurring extra parameters.
Rethinking Generalization in Few-Shot Classification
Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted.
Implicit Motion Handling for Video Camouflaged Object Detection
We propose a new video camouflaged object detection (VCOD) framework that can exploit both short-term dynamics and long-term temporal consistency to detect camouflaged objects from video frames.
Progressive Video Summarization via Multimodal Self-supervised Learning
Considering that the annotation of large-scale datasets is time-consuming, we propose a multimodal self-supervised learning framework to obtain semantic representations of videos, which benefits the video summarization task.
Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning
A principle way of achieving few-shot learning is to realize a model that can rapidly adapt to the context of a given task.
Adaptive Poincaré Point to Set Distance for Few-Shot Classification
To this end, we formulate the metric as a weighted sum on the tangent bundle of the hyperbolic space and develop a mechanism to obtain the weights adaptively and based on the constellation of the points.
Learning Online for Unified Segmentation and Tracking Models
A segmentation model cannot easily learn from prior information given in the visual tracking scenario.
IDENTIFYING CONCEALED OBJECTS FROM VIDEOS
The proposed SLT-Net leverages on both short-term dynamics and long-term temporal consistency to detect concealed objects in continuous video frames.
Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition
For example, there are estimated more than 40 different kinds of retinal diseases with variable morbidity, however with more than 30+ conditions are very rare from the global patient cohorts, which results in a typical long-tailed learning problem for deep learning-based screening models.
Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers
Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field.
Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
In this paper, we systematically discuss and define the two common types of label noise in medical images - disagreement label noise from inconsistency expert opinions and single-target label noise from wrong diagnosis record.
Leveraging Regular Fundus Images for Training UWF Fundus Diagnosis Models via Adversarial Learning and Pseudo-Labeling
We propose the use of a modified cycle generative adversarial network (CycleGAN) model to bridge the gap between regular and UWF fundus and generate additional UWF fundus images for training.
Localising In Complex Scenes Using Balanced Adversarial Adaptation
Domain adaptation and generative modelling have collectively mitigated the expensive nature of data collection and labelling by leveraging the rich abundance of accurate, labelled data in simulation environments.
Residual Likelihood Forests
This paper presents a novel ensemble learning approach called Residual Likelihood Forests (RLF).
Hierarchical Neural Architecture Search for Deep Stereo Matching
To reduce the human efforts in neural network design, Neural Architecture Search (NAS) has been applied with remarkable success to various high-level vision tasks such as classification and semantic segmentation.
Ranked #2 on
Stereo Disparity Estimation
on Scene Flow
Driving among Flatmobiles: Bird-Eye-View occupancy grids from a monocular camera for holistic trajectory planning
Camera-based end-to-end driving neural networks bring the promise of a low-cost system that maps camera images to driving control commands.
Supportive Actions for Manipulation in Human-Robot Coworker Teams
We compare two robot modes in a shared table pick-and-place task: (1) Task-oriented: the robot only takes actions to further its own task objective and (2) Supportive: the robot sometimes prefers supportive actions to task-oriented ones when they reduce future goal-conflicts.
Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation
We design a regularisation technique to regulate the domain adaptation.
Reducing the Sim-to-Real Gap for Event Cameras
We present strategies for improving training data for event based CNNs that result in 20-40% boost in performance of existing state-of-the-art (SOTA) video reconstruction networks retrained with our method, and up to 15% for optic flow networks.
OpenGAN: Open Set Generative Adversarial Networks
Using a state-of-the-art metric learning model that encodes both class-level and fine-grained semantic information, we are able to generate samples that are semantically similar to a given source image.
Switchable Precision Neural Networks
Instantaneous and on demand accuracy-efficiency trade-off has been recently explored in the context of neural networks slimming.
Automatic Pruning for Quantized Neural Networks
In particular, for ResNet-18 on ImageNet, we prune 26. 12% of the model size with Binarized Neural Network quantization, achieving a top-1 classification accuracy of 47. 32% in a model of 2. 47 MB and 59. 30% with a 2-bit DoReFa-Net in 4. 36 MB.
Adversarial Pulmonary Pathology Translation for Pairwise Chest X-ray Data Augmentation
We demonstrate the effectiveness of our model on two tasks: (i) we invite certified radiologists to assess the quality of the generated synthetic images against real and other state-of-the-art generative models, and (ii) data augmentation to improve the performance of disease localisation.
EMPNet: Neural Localisation and Mapping Using Embedded Memory Points
Continuously estimating an agent's state space and a representation of its surroundings has proven vital towards full autonomy.
Event-Based Motion Segmentation by Motion Compensation
In contrast to traditional cameras, whose pixels have a common exposure time, event-based cameras are novel bio-inspired sensors whose pixels work independently and asynchronously output intensity changes (called "events"), with microsecond resolution.
The Importance of Metric Learning for Robotic Vision: Open Set Recognition and Active Learning
Robotic problems are dynamic and open world; a robot will likely observe objects that are from outside of the training set distribution.
Look No Deeper: Recognizing Places from Opposing Viewpoints under Varying Scene Appearance using Single-View Depth Estimation
Visual place recognition (VPR) - the act of recognizing a familiar visual place - becomes difficult when there is extreme environmental appearance change or viewpoint change.
Robotics
Traversing Latent Space using Decision Ferns
The practice of transforming raw data to a feature space so that inference can be performed in that space has been popular for many years.
Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks
Furthermore, the proposed measurements also allow us to show that it is possible to optimise the training process with a new dynamic sampling training approach that continuously and automatically change the mini-batch size and learning rate during the training process.
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards.
Ranked #5 on
Real-Time Semantic Segmentation
on NYU Depth v2
CReaM: Condensed Real-time Models for Depth Prediction using Convolutional Neural Networks
At the time of writing, this is the first piece of work to showcase such a capability on a mobile platform.
ENG: End-to-end Neural Geometry for Robust Depth and Pose Estimation using CNNs
Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision.
Learning Factorized Representations for Open-set Domain Adaptation
To this end, we rely on the intuition that the source and target samples depicting the known classes can be generated by a shared subspace, whereas the target samples from unknown classes come from a different, private subspace.
Generative Adversarial Forests for Better Conditioned Adversarial Learning
In recent times, many of the breakthroughs in various vision-related tasks have revolved around improving learning of deep models; these methods have ranged from network architectural improvements such as Residual Networks, to various forms of regularisation such as Batch Normalisation.
Just-in-Time Reconstruction: Inpainting Sparse Maps using Single View Depth Predictors as Priors
Crucially, we obtain the confidence weights that parameterize the CRF model in a data-dependent manner via Convolutional Neural Networks (CNNs) which are trained to model the conditional depth error distributions given each source of input depth map and the associated RGB image.
Efficient Subpixel Refinement with Symbolic Linear Predictors
We present an efficient subpixel refinement method usinga learning-based approach called Linear Predictors.
Nearest Neighbour Radial Basis Function Solvers for Deep Neural Networks
The same loss function is used for both the metric learning and classification problems.
Joint Pose and Principal Curvature Refinement Using Quadrics
In this paper we present a novel joint approach for optimising surface curvature and pose alignment.
A Fast Method For Computing Principal Curvatures From Range Images
In particular we compare our method to several alternatives to demonstrate the improvement.
Joint Prediction of Depths, Normals and Surface Curvature from RGB Images using CNNs
To this end, we present a novel deep learning based framework that estimates depth, surface normals and surface curvature by only using a single RGB image.
Deep Metric Learning and Image Classification with Nearest Neighbour Gaussian Kernels
We present a Gaussian kernel loss function and training algorithm for convolutional neural networks that can be directly applied to both distance metric learning and image classification problems.
Smart Mining for Deep Metric Learning
In this paper, we propose a novel deep metric learning method that combines the triplet model and the global structure of the embedding space.
FANNG: Fast Approximate Nearest Neighbour Graphs
We also provide an efficient search algorithm that uses this graph to rapidly find the nearest neighbour to a query with high probability.
Faster and better: a machine learning approach to corner detection
The repeatability and efficiency of a corner detector determines how likely it is to be useful in a real-world application.
