no code implementations • 22 Nov 2022 • Yunyan Xing, Benjamin J. Meyer, Mehrtash Harandi, Tom Drummond, ZongYuan Ge
Medical imaging data, such as radiology images, are often multimorbidity; a single sample may have more than one pathology present.
1 code implementation • 9 Oct 2022 • Nicholas Rosa, Tom Drummond, Mehrtash Harandi
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.
1 code implementation • 25 Jul 2022 • Xuelian Cheng, Yiran Zhong, Mehrtash Harandi, Tom Drummond, Zhiyong Wang, ZongYuan Ge
The self-attention mechanism, successfully employed with the transformer structure is shown promise in many computer vision tasks including image recognition, and object detection.
no code implementations • 15 Jun 2022 • Markus Hiller, Mehrtash Harandi, Tom Drummond
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.
1 code implementation • 15 Jun 2022 • Markus Hiller, Rongkai Ma, Mehrtash Harandi, Tom Drummond
Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted.
no code implementations • CVPR 2022 • Xuelian Cheng, Huan Xiong, Deng-Ping Fan, Yiran Zhong, Mehrtash Harandi, Tom Drummond, ZongYuan Ge
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.
no code implementations • 7 Jan 2022 • Li Haopeng, Ke Qiuhong, Gong Mingming, Tom Drummond
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.
1 code implementation • 7 Dec 2021 • Rongkai Ma, Pengfei Fang, Gil Avraham, Yan Zuo, Tianyu Zhu, Tom Drummond, Mehrtash Harandi
A principle way of achieving few-shot learning is to realize a model that can rapidly adapt to the context of a given task.
no code implementations • 3 Dec 2021 • Rongkai Ma, Pengfei Fang, Tom Drummond, Mehrtash Harandi
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.
no code implementations • 12 Nov 2021 • Tianyu Zhu, Rongkai Ma, Mehrtash Harandi, Tom Drummond
A segmentation model cannot easily learn from prior information given in the visual tracking scenario.
no code implementations • 29 Sep 2021 • Xuelian Cheng, Huan Xiong, Deng-Ping Fan, Yiran Zhong, Mehrtash Harandi, Tom Drummond, ZongYuan Ge
The proposed SLT-Net leverages on both short-term dynamics and long-term temporal consistency to detect concealed objects in continuous video frames.
no code implementations • 22 Apr 2021 • Lie Ju, Xin Wang, Lin Wang, Tongliang Liu, Xin Zhao, Tom Drummond, Dwarikanath Mahapatra, ZongYuan Ge
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.
1 code implementation • 27 Mar 2021 • Tianyu Zhu, Markus Hiller, Mahsa Ehsanpour, Rongkai Ma, Tom Drummond, Ian Reid, Hamid Rezatofighi
Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field.
no code implementations • 28 Feb 2021 • Lie Ju, Xin Wang, Lin Wang, Dwarikanath Mahapatra, Xin Zhao, Mehrtash Harandi, Tom Drummond, Tongliang Liu, ZongYuan Ge
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.
no code implementations • 27 Nov 2020 • Lie Ju, Xin Wang, Xin Zhao, Paul Bonnington, Tom Drummond, ZongYuan Ge
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.
no code implementations • 9 Nov 2020 • Gil Avraham, Yan Zuo, Tom Drummond
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.
no code implementations • 4 Nov 2020 • Yan Zuo, Tom Drummond
This paper presents a novel ensemble learning approach called Residual Likelihood Forests (RLF).
1 code implementation • NeurIPS 2020 • Xuelian Cheng, Yiran Zhong, Mehrtash Harandi, Yuchao Dai, Xiaojun Chang, Tom Drummond, Hongdong Li, ZongYuan Ge
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
no code implementations • 10 Aug 2020 • Abdelhak Loukkal, Yves GRANDVALET, Tom Drummond, You Li
Camera-based end-to-end driving neural networks bring the promise of a low-cost system that maps camera images to driving control commands.
no code implementations • 2 May 2020 • Shray Bansal, Rhys Newbury, Wesley Chan, Akansel Cosgun, Aimee Allen, Dana Kulić, Tom Drummond, Charles Isbell
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.
no code implementations • 23 Mar 2020 • Lie Ju, Xin Wang, Quan Zhou, Hu Zhu, Mehrtash Harandi, Paul Bonnington, Tom Drummond, ZongYuan Ge
We design a regularisation technique to regulate the domain adaptation.
1 code implementation • ECCV 2020 • Timo Stoffregen, Cedric Scheerlinck, Davide Scaramuzza, Tom Drummond, Nick Barnes, Lindsay Kleeman, Robert Mahony
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.
2 code implementations • 18 Mar 2020 • Luke Ditria, Benjamin J. Meyer, Tom Drummond
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.
no code implementations • 7 Feb 2020 • Luis Guerra, Bohan Zhuang, Ian Reid, Tom Drummond
Instantaneous and on demand accuracy-efficiency trade-off has been recently explored in the context of neural networks slimming.
no code implementations • 3 Feb 2020 • Luis Guerra, Bohan Zhuang, Ian Reid, Tom Drummond
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.
1 code implementation • 11 Oct 2019 • Yunyan Xing, ZongYuan Ge, Rui Zeng, Dwarikanath Mahapatra, Jarrel Seah, Meng Law, Tom Drummond
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.
1 code implementation • ICCV 2019 • Gil Avraham, Yan Zuo, Thanuja Dharmasiri, Tom Drummond
Continuously estimating an agent's state space and a representation of its surroundings has proven vital towards full autonomy.
1 code implementation • ICCV 2019 • Timo Stoffregen, Guillermo Gallego, Tom Drummond, Lindsay Kleeman, Davide Scaramuzza
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.
no code implementations • 27 Feb 2019 • Benjamin J. Meyer, Tom Drummond
Robotic problems are dynamic and open world; a robot will likely observe objects that are from outside of the training set distribution.
1 code implementation • 20 Feb 2019 • Sourav Garg, Madhu Babu V, Thanuja Dharmasiri, Stephen Hausler, Niko Suenderhauf, Swagat Kumar, Tom Drummond, Michael Milford
Visual place recognition (VPR) - the act of recognizing a familiar visual place - becomes difficult when there is extreme environmental appearance change or viewpoint change.
no code implementations • 6 Dec 2018 • Yan Zuo, Gil Avraham, Tom Drummond
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.
1 code implementation • 16 Oct 2018 • Zhibin Liao, Tom Drummond, Ian Reid, Gustavo Carneiro
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.
3 code implementations • 13 Sep 2018 • Vladimir Nekrasov, Thanuja Dharmasiri, Andrew Spek, Tom Drummond, Chunhua Shen, Ian Reid
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
no code implementations • 24 Jul 2018 • Andrew Spek, Thanuja Dharmasiri, Tom Drummond
At the time of writing, this is the first piece of work to showcase such a capability on a mobile platform.
no code implementations • 16 Jul 2018 • Thanuja Dharmasiri, Andrew Spek, Tom Drummond
Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision.
no code implementations • ICLR 2019 • Mahsa Baktashmotlagh, Masoud Faraki, Tom Drummond, Mathieu Salzmann
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.
no code implementations • 14 May 2018 • Yan Zuo, Gil Avraham, Tom Drummond
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.
no code implementations • 11 May 2018 • Chamara Saroj Weerasekera, Thanuja Dharmasiri, Ravi Garg, Tom Drummond, Ian Reid
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.
no code implementations • CVPR 2018 • Vincent Lui, Jonathon Geeves, Winston Yii, Tom Drummond
We present an efficient subpixel refinement method usinga learning-based approach called Linear Predictors.
no code implementations • ICLR 2018 • Benjamin J. Meyer, Ben Harwood, Tom Drummond
The same loss function is used for both the metric learning and classification problems.
1 code implementation • 3 Jul 2017 • Andrew Spek, Tom Drummond
In this paper we present a novel joint approach for optimising surface curvature and pose alignment.
1 code implementation • 3 Jul 2017 • Andrew Spek, Wai Ho Li, Tom Drummond
In particular we compare our method to several alternatives to demonstrate the improvement.
no code implementations • 23 Jun 2017 • Thanuja Dharmasiri, Andrew Spek, Tom Drummond
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.
no code implementations • 27 May 2017 • Benjamin J. Meyer, Ben Harwood, Tom Drummond
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.
no code implementations • ICCV 2017 • Ben Harwood, Vijay Kumar B G, Gustavo Carneiro, Ian Reid, Tom Drummond
In this paper, we propose a novel deep metric learning method that combines the triplet model and the global structure of the embedding space.
no code implementations • CVPR 2016 • Ben Harwood, Tom Drummond
We also provide an efficient search algorithm that uses this graph to rapidly find the nearest neighbour to a query with high probability.
1 code implementation • 14 Oct 2008 • Edward Rosten, Reid Porter, Tom Drummond
The repeatability and efficiency of a corner detector determines how likely it is to be useful in a real-world application.