no code implementations • VarDial (COLING) 2020 • Bharathi Raja Chakravarthi, Navaneethan Rajasekaran, Mihael Arcan, Kevin McGuinness, Noel E. O’Connor, John P. McCrae
Bilingual lexicons are a vital tool for under-resourced languages and recent state-of-the-art approaches to this leverage pretrained monolingual word embeddings using supervised or semi-supervised approaches.
1 code implementation • 8 Jul 2024 • Paul Albert, Jack Valmadre, Eric Arazo, Tarun Krishna, Noel E. O'Connor, Kevin McGuinness
Training a classifier on web-crawled data demands learning algorithms that are robust to annotation errors and irrelevant examples.
1 code implementation • 14 Feb 2024 • Qiang Wang, Yixin Deng, Francisco Roldan Sanchez, Keru Wang, Kevin McGuinness, Noel O'Connor, Stephen J. Redmond
Offline policy learning aims to discover decision-making policies from previously-collected datasets without additional online interactions with the environment.
no code implementations • 27 Nov 2023 • Ayush K. Rai, Tarun Krishna, Feiyan Hu, Alexandru Drimbarean, Kevin McGuinness, Alan F. Smeaton, Noel E. O'Connor
Video Anomaly Detection (VAD) is an open-set recognition task, which is usually formulated as a one-class classification (OCC) problem, where training data is comprised of videos with normal instances while test data contains both normal and anomalous instances.
1 code implementation • 3 Oct 2023 • Francisco Roldan Sanchez, Qiang Wang, David Cordova Bulens, Kevin McGuinness, Stephen Redmond, Noel O'Connor
Hindsight Experience Replay (HER) is a technique used in reinforcement learning (RL) that has proven to be very efficient for training off-policy RL-based agents to solve goal-based robotic manipulation tasks using sparse rewards.
no code implementations • 22 Jul 2023 • Enric Moreu, Eric Arazo, Kevin McGuinness, Noel E. O'Connor
To address both challenges, we leverage synthetic data and propose an end-to-end model for polyp segmentation that integrates real and synthetic data to artificially increase the size of the datasets and aid the training when unlabeled samples are available.
1 code implementation • 21 Jul 2023 • Mayug Maniparambil, Chris Vorster, Derek Molloy, Noel Murphy, Kevin McGuinness, Noel E. O'Connor
Meanwhile, recent developments in generative pretrained models like GPT-4 mean they can be used as advanced internet search tools.
no code implementations • 20 Jul 2023 • Enric Moreu, Eric Arazo, Kevin McGuinness, Noel E. O'Connor
We take advantage of recent one-sided translation models because they use significantly less memory, allowing us to add a segmentation model in the training loop.
1 code implementation • 17 May 2023 • Sidra Aleem, Mayug Maniparambil, Suzanne Little, Noel O'Connor, Kevin McGuinness
Chest X-rays have been widely used for COVID-19 screening; however, 3D computed tomography (CT) is a more effective modality.
no code implementations • 2 Feb 2023 • Conor Brennan, Kevin McGuinness
This paper describes deep learning models based on convolutional neural networks applied to the problem of predicting EM wave propagation over rural terrain.
1 code implementation • 30 Jan 2023 • Qiang Wang, Robert McCarthy, David Cordova Bulens, Francisco Roldan Sanchez, Kevin McGuinness, Noel E. O'Connor, Stephen J. Redmond
However, BC's performance deteriorated when applied to mixed datasets, and the performance of offline RL algorithms was also unsatisfactory.
no code implementations • 27 Jan 2023 • Qiang Wang, Robert McCarthy, David Cordova Bulens, Kevin McGuinness, Noel E. O'Connor, Nico Gürtler, Felix Widmaier, Francisco Roldan Sanchez, Stephen J. Redmond
Learning control policies offline from pre-recorded datasets is a promising avenue for solving challenging real-world problems.
1 code implementation • 22 Jan 2023 • Tarun Krishna, Ayush K Rai, Alexandru Drimbarean, Eric Arazo, Paul Albert, Alan F Smeaton, Kevin McGuinness, Noel E O'Connor
Computationally expensive training strategies make self-supervised learning (SSL) impractical for resource constrained industrial settings.
1 code implementation • 11 Jan 2023 • Feiyan Hu, Simone Palazzo, Federica Proietto Salanitri, Giovanni Bellitto, Morteza Moradi, Concetto Spampinato, Kevin McGuinness
Video saliency prediction has recently attracted attention of the research community, as it is an upstream task for several practical applications.
1 code implementation • 11 Oct 2022 • Ayush K. Rai, Tarun Krishna, Julia Dietlmeier, Kevin McGuinness, Alan F. Smeaton, Noel E. O'Connor
In this work, we address this issue by revisiting a simple and effective self-supervised method and augment it with a differentiable motion feature learning module to tackle the spatial and temporal diversities in the GEBD task.
2 code implementations • 10 Oct 2022 • Paul Albert, Eric Arazo, Tarun Krishna, Noel E. O'Connor, Kevin McGuinness
Experiments demonstrate the state-of-the-art performance of our Pseudo-Loss Selection (PLS) algorithm on a variety of benchmark datasets including curated data synthetically corrupted with in-distribution and out-of-distribution noise, and two real world web noise datasets.
1 code implementation • 5 Oct 2022 • Mayug Maniparambil, Kevin McGuinness, Noel O'Connor
In this paper we propose to make use of the well-trained feature representations of the base dataset that are closest to each support instance to improve its representation during meta-test time.
1 code implementation • 3 Oct 2022 • Sidra Aleem, Teerath Kumar, Suzanne Little, Malika Bendechache, Rob Brennan, Kevin McGuinness
To evaluate the generalization of the proposed method, we use four medical datasets and compare its performance with state-of-the-art methods for both classification and segmentation tasks.
1 code implementation • 2 Oct 2022 • Ashish Singh, Antonio Bevilacqua, Thach Le Nguyen, Feiyan Hu, Kevin McGuinness, Martin OReilly, Darragh Whelan, Brian Caulfield, Georgiana Ifrim
We analyze the accuracy and robustness of BodyMTS and show that it is robust to different types of noise caused by either video quality or pose estimation factors.
no code implementations • 20 Sep 2022 • Carles Garcia-Cabrera, Eric Arazo, Kathleen M. Curran, Noel E. O'Connor, Kevin McGuinness
Methods that are resilient to artifacts in the cardiac magnetic resonance imaging (MRI) while performing ventricle segmentation, are crucial for ensuring quality in structural and functional analysis of those tissues.
1 code implementation • 25 Jul 2022 • Tarun Krishna, Ayush K. Rai, Yasser A. D. Djilali, Alan F. Smeaton, Kevin McGuinness, Noel E. O'Connor
Currently, convnets pre-trained with self-supervision have obtained comparable performance on downstream tasks in comparison to their supervised counterparts in computer vision.
1 code implementation • 4 Jul 2022 • Paul Albert, Eric Arazo, Noel E. O'Connor, Kevin McGuinness
These noisy samples have been evidenced by previous works to be a mixture of in-distribution (ID) samples, assigned to the incorrect category but presenting similar visual semantics to other classes in the dataset, and out-of-distribution (OOD) images, which share no semantic correlation with any category from the dataset.
no code implementations • 9 Jun 2022 • Eric Arazo, Robin Aly, Kevin McGuinness
Cow lameness is a severe condition that affects the life cycle and life quality of dairy cows and results in considerable economic losses.
1 code implementation • 19 May 2022 • Qiang Wang, Francisco Roldan Sanchez, Robert McCarthy, David Cordova Bulens, Kevin McGuinness, Noel O'Connor, Manuel Wüthrich, Felix Widmaier, Stefan Bauer, Stephen J. Redmond
Here we extend this method, by modifying the task of Phase 1 of the RRC to require the robot to maintain the cube in a particular orientation, while the cube is moved along the required positional trajectory.
no code implementations • 20 Apr 2022 • Paul Albert, Mohamed Saadeldin, Badri Narayanan, Brian Mac Namee, Deirdre Hennessy, Aisling H. O'Connor, Noel E. O'Connor, Kevin McGuinness
Sward species composition estimation is a tedious one.
1 code implementation • 18 Apr 2022 • Paul Albert, Mohamed Saadeldin, Badri Narayanan, Jaime Fernandez, Brian Mac Namee, Deirdre Hennessey, Noel E. O'Connor, Kevin McGuinness
In this context, deep learning algorithms offer a tempting alternative to the usual means of sward composition estimation, which involves the destructive process of cutting a sample from the herbage field and sorting by hand all plant species in the herbage.
1 code implementation • 17 Feb 2022 • Enric Moreu, Kevin McGuinness, Diego Ortego, Noel E. O'Connor
We introduce a domain randomization approach for object counting based on synthetic datasets that are quick and inexpensive to generate.
1 code implementation • 17 Feb 2022 • Enric Moreu, Kevin McGuinness, Noel E. O'Connor
Deep learning has shown excellent performance in analysing medical images.
1 code implementation • LREC 2022 • Luis Lebron, Yvette Graham, Kevin McGuinness, Konstantinos Kouramas, Noel E. O'Connor
The model is based on BERT, which is a language model that has been shown to work well in multiple NLP tasks.
no code implementations • 17 Nov 2021 • Julia Dietlmeier, Feiyan Hu, Frances Ryan, Noel E. O'Connor, Kevin McGuinness
We apply state-of-the-art person re-identification models to our dataset and show that by leveraging the available timestamp information we are able to achieve a significant gain of 37. 43% in mAP and a gain of 30. 22% in Rank1 accuracy.
1 code implementation • 27 Oct 2021 • Eric Arazo, Diego Ortego, Paul Albert, Noel E. O'Connor, Kevin McGuinness
We suggest that, given a specific budget, the best course of action is to disregard the importance and introduce adequate data augmentation; e. g. when reducing the budget to a 30% in CIFAR-10/100, RICAP data augmentation maintains accuracy, while importance sampling does not.
no code implementations • 26 Oct 2021 • Paul Albert, Diego Ortego, Eric Arazo, Noel O'Connor, Kevin McGuinness
We propose a simple solution to bridge the gap with a fully clean dataset using Dynamic Softening of Out-of-distribution Samples (DSOS), which we design on corrupted versions of the CIFAR-100 dataset, and compare against state-of-the-art algorithms on the web noise perturbated MiniImageNet and Stanford datasets and on real label noise datasets: WebVision 1. 0 and Clothing1M.
no code implementations • 26 Oct 2021 • Paul Albert, Mohamed Saadeldin, Badri Narayanan, Brian Mac Namee, Deirdre Hennessy, Aisling O'Connor, Noel O'Connor, Kevin McGuinness
Deep learning for computer vision is a powerful tool in this context as it can accurately estimate the dry biomass of a herbage parcel using images of the grass canopy taken using a portable device.
2 code implementations • 30 Sep 2021 • Robert McCarthy, Francisco Roldan Sanchez, Qiang Wang, David Cordova Bulens, Kevin McGuinness, Noel O'Connor, Stephen J. Redmond
This paper details our winning submission to Phase 1 of the 2021 Real Robot Challenge; a challenge in which a three-fingered robot must carry a cube along specified goal trajectories.
no code implementations • 18 Jun 2021 • Ayush K Rai, Tarun Krishna, Julia Dietlmeier, Kevin McGuinness, Alan F Smeaton, Noel E O'Connor
Detecting generic, taxonomy-free event boundaries invideos represents a major stride forward towards holisticvideo understanding.
no code implementations • 30 Apr 2021 • Tarun Krishna, Kevin McGuinness, Noel O'Connor
In this work, we evaluate contrastive models for the task of image retrieval.
no code implementations • 8 Jan 2021 • Badri Narayanan, Mohamed Saadeldin, Paul Albert, Kevin McGuinness, Brian Mac Namee
In this paper, we demonstrate that applying data augmentation and transfer learning is effective in predicting multi-target biomass percentages of different plant species, even with a small training dataset.
1 code implementation • ICCV 2021 • Yasser Abdelaziz Dahou Djilali, Tarun Krishna, Kevin McGuinness, Noel E. O'Connor
This performance is achieved using an encoder that is trained in a completely unsupervised way and a relatively lightweight supervised decoder (3. 8 X fewer parameters in the case of the ResNet50 encoder).
no code implementations • 1 Jan 2021 • Eric Arazo, Diego Ortego, Paul Albert, Noel O'Connor, Kevin McGuinness
For example, training in CIFAR-10/100 with 30% of the full training budget, a uniform sampling strategy with certain data augmentation surpasses the performance of 100% budget models trained with standard data augmentation.
no code implementations • 18 Dec 2020 • Feiyan Hu, Eva Mohedano, Noel O'Connor, Kevin McGuinness
Current deep learning based video classification architectures are typically trained end-to-end on large volumes of data and require extensive computational resources.
1 code implementation • CVPR 2021 • Diego Ortego, Eric Arazo, Paul Albert, Noel E. O'Connor, Kevin McGuinness
We further propose a novel label noise detection method that exploits the robust feature representations learned via contrastive learning to estimate per-sample soft-labels whose disagreements with the original labels accurately identify noisy samples.
Ranked #22 on
Image Classification
on mini WebVision 1.0
1 code implementation • 20 Nov 2020 • Yasser Dahou, Marouane Tliba, Kevin McGuinness, Noel O'Connor
The spherical domain representation of 360 video/image presents many challenges related to the storage, processing, transmission and rendering of omnidirectional videos (ODV).
1 code implementation • 15 Nov 2020 • Eduardo Fonseca, Diego Ortego, Kevin McGuinness, Noel E. O'Connor, Xavier Serra
Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research.
no code implementations • 13 Oct 2020 • Julia Dietlmeier, Joseph Antony, Kevin McGuinness, Noel E. O'Connor
This paper investigates the dependence of existing state-of-the-art person re-identification models on the presence and visibility of human faces.
1 code implementation • 5 Oct 2020 • David Azcona, Kevin McGuinness, Alan F. Smeaton
Overall we achieved a performance of 93. 4% AUC on the validation data by using the more recent deep learning architectures and data augmentation strategies.
1 code implementation • 25 Aug 2020 • Feiyan Hu, Kevin McGuinness
This paper focuses on the problem of visual saliency prediction, predicting regions of an image that tend to attract human visual attention, under a constrained computational budget.
1 code implementation • 23 Jul 2020 • Paul Albert, Diego Ortego, Eric Arazo, Noel E. O'Connor, Kevin McGuinness
We propose Reliable Label Bootstrapping (ReLaB), an unsupervised preprossessing algorithm which improves the performance of semi-supervised algorithms in extremely low supervision settings.
no code implementations • 1 May 2020 • Mark Marsden, Kevin McGuinness, Joseph Antony, Haolin Wei, Milan Redzic, Jian Tang, Zhilan Hu, Alan Smeaton, Noel E. O'Connor
This work investigates the use of class-level difficulty factors in multi-label classification problems for the first time.
1 code implementation • 18 Dec 2019 • Diego Ortego, Eric Arazo, Paul Albert, Noel E. O'Connor, Kevin McGuinness
However, we show that different noise distributions make the application of this trick less straightforward and propose to continuously relabel all images to reveal a discriminative loss against multiple distributions.
no code implementations • 25 Oct 2019 • Panagiotis Linardos, Suzanne Little, Kevin McGuinness
This work tackles the Pixel Privacy task put forth by MediaEval 2019.
no code implementations • 23 Aug 2019 • Joseph Antony, Kevin McGuinness, Kieran Moran, Noel E O' Connor
Also, this chapter demonstrates that feature learning in a supervised manner is more effective than using conventional handcrafted features for automatic detection of knee joints and fine-grained knee OA image classification.
1 code implementation • 23 Aug 2019 • Marc Górriz, Joseph Antony, Kevin McGuinness, Xavier Giró-i-Nieto, Noel E. O'Connor
This work proposes a novel end-to-end convolutional neural network (CNN) architecture to automatically quantify the severity of knee osteoarthritis (OA) using X-Ray images, which incorporates trainable attention modules acting as unsupervised fine-grained detectors of the region of interest (ROI).
no code implementations • 23 Aug 2019 • Jaynal Abedin, Joseph Antony, Kevin McGuinness, Kieran Moran, Noel E. O'Connor, Dietrich Rebholz-Schuhmann, John Newell
Knee osteoarthritis (KOA) is a disease that impairs knee function and causes pain.
4 code implementations • 8 Aug 2019 • Eric Arazo, Diego Ortego, Paul Albert, Noel E. O'Connor, Kevin McGuinness
In the context of image classification, recent advances to learn from unlabeled samples are mainly focused on consistency regularization methods that encourage invariant predictions for different perturbations of unlabeled samples.
2 code implementations • 3 Jul 2019 • Panagiotis Linardos, Eva Mohedano, Juan Jose Nieto, Noel E. O'Connor, Xavier Giro-i-Nieto, Kevin McGuinness
This paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain.
no code implementations • 25 Apr 2019 • Diego Ortego, Kevin McGuinness, Juan C. SanMiguel, Eric Arazo, José M. Martínez, Noel E. O'Connor
This guiding process relies on foreground masks from independent algorithms (i. e. state-of-the-art algorithms) to implement an attention mechanism that incorporates the spatial location of foreground and background to compute their separated representations.
2 code implementations • 25 Apr 2019 • Eric Arazo, Diego Ortego, Paul Albert, Noel E. O'Connor, Kevin McGuinness
Specifically, we propose a beta mixture to estimate this probability and correct the loss by relying on the network prediction (the so-called bootstrapping loss).
Ranked #44 on
Image Classification
on Clothing1M
1 code implementation • 18 Apr 2019 • Federico Magliani, Kevin McGuinness, Eva Mohedano, Andrea Prati
The application of the diffusion in many computer vision and artificial intelligence projects has been shown to give excellent improvements in performance.
3 code implementations • 25 Mar 2019 • Amanda Duarte, Francisco Roldan, Miquel Tubau, Janna Escur, Santiago Pascual, Amaia Salvador, Eva Mohedano, Kevin McGuinness, Jordi Torres, Xavier Giro-i-Nieto
Speech is a rich biometric signal that contains information about the identity, gender and emotional state of the speaker.
1 code implementation • 3 Sep 2018 • Marc Assens, Xavier Giro-i-Nieto, Kevin McGuinness, Noel E. O'Connor
We introduce PathGAN, a deep neural network for visual scanpath prediction trained on adversarial examples.
1 code implementation • 29 Nov 2017 • Eva Mohedano, Kevin McGuinness, Xavier Giro-i-Nieto, Noel E. O'Connor
This work explores attention models to weight the contribution of local convolutional representations for the instance search task.
no code implementations • CVPR 2018 • Mark Marsden, Kevin McGuinness, Suzanne Little, Ciara E. Keogh, Noel E. O'Connor
In this paper we propose a technique to adapt a convolutional neural network (CNN) based object counter to additional visual domains and object types while still preserving the original counting function.
1 code implementation • 11 Jul 2017 • Marc Assens, Kevin McGuinness, Xavier Giro-i-Nieto, Noel E. O'Connor
The first part of the network consists of a model trained to generate saliency volumes, whose parameters are fit by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency volumes.
1 code implementation • 30 May 2017 • Mark Marsden, Kevin McGuinness, Suzanne Little, Noel E. O'Connor
In this paper we propose ResnetCrowd, a deep residual architecture for simultaneous crowd counting, violent behaviour detection and crowd density level classification.
no code implementations • 29 Mar 2017 • Joseph Antony, Kevin McGuinness, Kieran Moran, Noel E. O'Connor
We introduce a new approach to automatically detect the knee joints using a fully convolutional neural network (FCN).
4 code implementations • 4 Jan 2017 • Junting Pan, Cristian Canton Ferrer, Kevin McGuinness, Noel E. O'Connor, Jordi Torres, Elisa Sayrol, Xavier Giro-i-Nieto
We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples.
no code implementations • 1 Dec 2016 • Mark Marsden, Kevin McGuinness, Suzanne Little, Noel E. O'Connor
In this paper we advance the state-of-the-art for crowd counting in high density scenes by further exploring the idea of a fully convolutional crowd counting model introduced by (Zhang et al., 2016).
no code implementations • 9 Sep 2016 • Joseph Antony, Kevin McGuinness, Neil Welch, Joe Coyle, Andy Franklyn-Miller, Noel E. O'Connor, Kieran Moran
In this paper, we propose a method to precisely quantify the fat deposition / infiltration in a user-defined region of the lumbar muscles, which may aid better diagnosis and analysis.
no code implementations • 8 Sep 2016 • Joseph Antony, Kevin McGuinness, Noel E O Connor, Kieran Moran
We demonstrate that classification accuracy can be significantly improved using deep convolutional neural network models pre-trained on ImageNet and fine-tuned on knee OA images.
no code implementations • 29 Aug 2016 • Cristian Reyes, Eva Mohedano, Kevin McGuinness, Noel E. O'Connor, Xavier Giro-i-Nieto
This work presents a retrieval pipeline and evaluation scheme for the problem of finding the last appearance of personal objects in a large dataset of images captured from a wearable camera.
2 code implementations • 15 Apr 2016 • Eva Mohedano, Amaia Salvador, Kevin McGuinness, Ferran Marques, Noel E. O'Connor, Xavier Giro-i-Nieto
This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW).
1 code implementation • CVPR 2016 • Junting Pan, Kevin McGuinness, Elisa Sayrol, Noel O'Connor, Xavier Giro-i-Nieto
The prediction of salient areas in images has been traditionally addressed with hand-crafted features based on neuroscience principles.
no code implementations • 27 May 2015 • Carles Ventura, Xavier Giró-i-Nieto, Verónica Vilaplana, Kevin McGuinness, Ferran Marqués, Noel E. O'Connor
This paper explores novel approaches for improving the spatial codification for the pooling of local descriptors to solve the semantic segmentation problem.
no code implementations • 9 Apr 2015 • Eva Mohedano, Amaia Salvador, Sergi Porta, Xavier Giró-i-Nieto, Graham Healy, Kevin McGuinness, Noel O'Connor, Alan F. Smeaton
We show that it is indeed possible to detect such objects in complex images and, also, that users with previous knowledge on the dataset or experience with the RSVP outperform others.
no code implementations • 19 Aug 2014 • Eva Mohedano, Graham Healy, Kevin McGuinness, Xavier Giro-i-Nieto, Noel E. O'Connor, Alan F. Smeaton
This paper explores the potential of brain-computer interfaces in segmenting objects from images.