Search Results for author: Noel E. O'Connor

Found 54 papers, 28 papers with code

Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach

no code implementations27 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.

One-Class Classification Open Set Learning +2

Self-Supervised and Semi-Supervised Polyp Segmentation using Synthetic Data

no code implementations22 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.

Image-to-Image Translation Segmentation

Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts

1 code implementation21 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.

Descriptive Prompt Engineering +1

Joint one-sided synthetic unpaired image translation and segmentation for colorectal cancer prevention

no code implementations20 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.

Segmentation Translation

Motion Aware Self-Supervision for Generic Event Boundary Detection

1 code implementation11 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.

Boundary Detection Generic Event Boundary Detection

Is your noise correction noisy? PLS: Robustness to label noise with two stage detection

2 code implementations10 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.

Pseudo Label

Cardiac Segmentation using Transfer Learning under Respiratory Motion Artifacts

no code implementations20 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.

Cardiac Segmentation Transfer Learning

Dynamic Channel Selection in Self-Supervised Learning

1 code implementation25 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.

Image Classification Self-Supervised Learning

Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets

1 code implementation4 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.

Clustering Contrastive Learning +2

Unsupervised domain adaptation and super resolution on drone images for autonomous dry herbage biomass estimation

1 code implementation18 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.

Super-Resolution Unsupervised Domain Adaptation

Synthetic data for unsupervised polyp segmentation

1 code implementation17 Feb 2022 Enric Moreu, Kevin McGuinness, Noel E. O'Connor

Deep learning has shown excellent performance in analysing medical images.

Segmentation

Domain Randomization for Object Counting

1 code implementation17 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.

Object Object Counting

Improving Person Re-Identification with Temporal Constraints

no code implementations17 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.

Person Re-Identification Re-Ranking

How Important is Importance Sampling for Deep Budgeted Training?

1 code implementation27 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.

Data Augmentation

Attention-Based Neural Networks for Chroma Intra Prediction in Video Coding

no code implementations9 Feb 2021 Marc Górriz, Saverio Blasi, Alan F. Smeaton, Noel E. O'Connor, Marta Mrak

Simplifications include a framework for reducing the overhead of the convolutional operations, a simplified cross-component processing model integrated into the original architecture, and a methodology to perform integer-precision approximations with the aim to obtain fast and hardware-aware implementations.

Rethinking 360deg Image Visual Attention Modelling With Unsupervised Learning.

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).

Contrastive Learning Representation Learning +1

Investigating Memorability of Dynamic Media

no code implementations31 Dec 2020 Phuc H. Le-Khac, Ayush K. Rai, Graham Healy, Alan F. Smeaton, Noel E. O'Connor

The Predicting Media Memorability task in MediaEval'20 has some challenging aspects compared to previous years.

Multi-Objective Interpolation Training for Robustness to Label Noise

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.

Contrastive Learning Image Classification +3

Unsupervised Contrastive Learning of Sound Event Representations

1 code implementation15 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.

Contrastive Learning Representation Learning

How important are faces for person re-identification?

no code implementations13 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.

Computational Efficiency Face Detection +1

Utilising Visual Attention Cues for Vehicle Detection and Tracking

no code implementations31 Jul 2020 Feiyan Hu, Venkatesh G M, Noel E. O'Connor, Alan F. Smeaton, Suzanne Little

We investigate: 1) How a visual attention map such as a \emph{subjectness} attention or saliency map and an \emph{objectness} attention map can facilitate region proposal generation in a 2-stage object detector; 2) How a visual attention map can be used for tracking multiple objects.

Object object-detection +2

Reliable Label Bootstrapping for Semi-Supervised Learning

1 code implementation23 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.

Self-Supervised Learning

Towards Robust Learning with Different Label Noise Distributions

1 code implementation18 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.

Memorization Representation Learning

End-to-End Conditional GAN-based Architectures for Image Colourisation

1 code implementation26 Aug 2019 Marc Górriz, Marta Mrak, Alan F. Smeaton, Noel E. O'Connor

In this work recent advances in conditional adversarial networks are investigated to develop an end-to-end architecture based on Convolutional Neural Networks (CNNs) to directly map realistic colours to an input greyscale image.

Assessing Knee OA Severity with CNN attention-based end-to-end architectures

1 code implementation23 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).

Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning

4 code implementations8 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.

Image Classification

Simple vs complex temporal recurrences for video saliency prediction

2 code implementations3 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.

Saliency Prediction Video Saliency Detection +1

Unsupervised Label Noise Modeling and Loss Correction

2 code implementations25 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).

Image Classification

On guiding video object segmentation

no code implementations25 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.

Foreground Segmentation Object +5

PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks

1 code implementation3 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.

Scanpath prediction

Saliency Weighted Convolutional Features for Instance Search

1 code implementation29 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.

Instance Search Retrieval

People, Penguins and Petri Dishes: Adapting Object Counting Models To New Visual Domains And Object Types Without Forgetting

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.

Cultural Vocal Bursts Intensity Prediction Object +1

SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes

1 code implementation11 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.

Scanpath prediction

ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification

1 code implementation30 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.

Crowd Counting General Classification

Fully Convolutional Crowd Counting On Highly Congested Scenes

no code implementations1 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).

Crowd Counting

An Interactive Segmentation Tool for Quantifying Fat in Lumbar Muscles using Axial Lumbar-Spine MRI

no code implementations9 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.

Interactive Segmentation Variable Selection

Where is my Phone ? Personal Object Retrieval from Egocentric Images

no code implementations29 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.

Retrieval

Bags of Local Convolutional Features for Scalable Instance Search

2 code implementations15 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).

Instance Search Retrieval

Improving Spatial Codification in Semantic Segmentation

no code implementations27 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.

Object Segmentation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.