no code implementations • 28 Mar 2024 • Ozgu Goksu, Nicolas Pugeault
The pursuit of learning robust representations without human supervision is a longstanding challenge.
1 code implementation • 19 Jan 2023 • Antanas Kascenas, Pedro Sanchez, Patrick Schrempf, Chaoyang Wang, William Clackett, Shadia S. Mikhael, Jeremy P. Voisey, Keith Goatman, Alexander Weir, Nicolas Pugeault, Sotirios A. Tsaftaris, Alison Q. O'Neil
Denoising methods, for instance classical denoising autoencoders (DAEs) and more recently emerging diffusion models, are a promising approach, however naive application of pixelwise noise leads to poor anomaly detection performance.
no code implementations • 25 Jan 2022 • Charlie Kirkwood, Theo Economou, Henry Odbert, Nicolas Pugeault
However, as the number of available observation sites increases, so too does the opportunity for data quality issues to emerge, particularly given that many of these sensors do not have the benefit of official maintenance teams.
no code implementations • 13 Nov 2020 • Faisal Alamri, Sinan Kalkan, Nicolas Pugeault
Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low amplitude perturbations, barely perceptible by the human eye, can lead to a drastic reduction in labeling performance.
no code implementations • 17 Aug 2020 • Charlie Kirkwood, Theo Economou, Nicolas Pugeault
Here we demonstrate the power of feature learning in a geostatistical context, by showing how deep neural networks can automatically learn the complex relationships between point-sampled target variables and gridded auxiliary variables (such as those provided by remote sensing), and in doing so produce detailed maps of chosen target variables.
1 code implementation • 12 May 2020 • Mohammad Rami Koujan, Luma Alharbawee, Giorgos Giannakakis, Nicolas Pugeault, Anastasios Roussos
Human emotions analysis has been the focus of many studies, especially in the field of Affective Computing, and is important for many applications, e. g. human-computer intelligent interaction, stress analysis, interactive games, animations, etc.
1 code implementation • 6 May 2020 • Charlie Kirkwood, Theo Economou, Henry Odbert, Nicolas Pugeault
In this paper, we use a road surface temperature example to demonstrate a three-stage framework that uses machine learning to bridge the gap between sets of separate forecasts from NWP models and the 'ideal' forecast for decision support: probabilities of future weather outcomes.
2 code implementations • 29 Apr 2020 • Sen He, Wentong Liao, Hamed R. -Tavakoli, Michael Yang, Bodo Rosenhahn, Nicolas Pugeault
Inspired by the successes in text analysis and translation, previous work have proposed the \textit{transformer} architecture for image captioning.
no code implementations • 6 Jun 2019 • Faisal Alamri, Nicolas Pugeault
Contextual information, such as the co-occurrence of objects and the spatial and relative size among objects provides deep and complex information about scenes.
no code implementations • ICCV 2019 • Sen He, Hamed R. -Tavakoli, Ali Borji, Nicolas Pugeault
In this work, we present a novel dataset consisting of eye movements and verbal descriptions recorded synchronously over images.
1 code implementation • CVPR 2019 • Sen He, Hamed R. -Tavakoli, Ali Borji, Yang Mi, Nicolas Pugeault
Our analyses reveal that: 1) some visual regions (e. g. head, text, symbol, vehicle) are already encoded within various layers of the network pre-trained for object recognition, 2) using modern datasets, we find that fine-tuning pre-trained models for saliency prediction makes them favor some categories (e. g. head) over some others (e. g. text), 3) although deep models of saliency outperform classical models on natural images, the converse is true for synthetic stimuli (e. g. pop-out search arrays), an evidence of significant difference between human and data-driven saliency models, and 4) we confirm that, after-fine tuning, the change in inner-representations is mostly due to the task and not the domain shift in the data.
2 code implementations • ICLR 2019 • Dmitry Kangin, Nicolas Pugeault
Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies.
no code implementations • 15 Mar 2018 • Sen He, Ali Borji, Yang Mi, Nicolas Pugeault
Deep convolutional neural networks have demonstrated high performances for fixation prediction in recent years.
no code implementations • 15 Mar 2018 • Sen He, Dmitry Kangin, Yang Mi, Nicolas Pugeault
In this paper, we apply the attention mechanism to autonomous driving for steering angle prediction.
no code implementations • 15 Mar 2018 • Sen He, Nicolas Pugeault
Early saliency models were based on low-level hand-crafted feature derived from insights gained in neuroscience and psychophysics.
no code implementations • 12 Jan 2018 • Sen He, Nicolas Pugeault
Moreover we argue that this transformation leads to the emergence of receptive fields conceptually similar to the centre-surround filters hypothesized by early research on visual saliency.
no code implementations • ICLR 2018 • Dmitry Kangin, Nicolas Pugeault
In this article we propose a model-free control method, which uses a combination of reinforcement and supervised learning for autonomous control and paves the way towards policy based control in real world environments.
no code implementations • ICCV 2017 • Oscar Mendez, Simon Hadfield, Nicolas Pugeault, Richard Bowden
This approach is ill-suited for reconstruction applications, where learning about the environment is more valuable than speed of traversal.
no code implementations • 5 Sep 2017 • Oscar Mendez, Simon Hadfield, Nicolas Pugeault, Richard Bowden
Similarly, we do not extrude the 2D geometry present in the floorplan into 3D and try to align it to the real-world.
no code implementations • CVPR 2014 • Eng-Jon Ong, Oscar Koller, Nicolas Pugeault, Richard Bowden
This paper tackles the problem of spotting a set of signs occuring in videos with sequences of signs.