Search Results for author: Lars Petersson

Found 79 papers, 23 papers with code

Deep Learning Approaches for Seizure Video Analysis: A Review

no code implementations18 Dec 2023 David Ahmedt-Aristizabal, Mohammad Ali Armin, Zeeshan Hayder, Norberto Garcia-Cairasco, Lars Petersson, Clinton Fookes, Simon Denman, Aileen McGonigal

Historically, these approaches have been used for disease detection, classification, and prediction using diagnostic data; however, there has been limited exploration of their application in evaluating video-based motion detection in the clinical epileptology setting.

Decision Making Motion Detection +1

A Multimodal Dataset and Benchmark for Radio Galaxy and Infrared Host Detection

3 code implementations11 Dec 2023 Nikhel Gupta, Zeeshan Hayder, Ray P. Norris, Minh Hyunh, Lars Petersson

We present a novel multimodal dataset developed by expert astronomers to automate the detection and localisation of multi-component extended radio galaxies and their corresponding infrared hosts.

object-detection Object Detection +1

RadioGalaxyNET: Dataset and Novel Computer Vision Algorithms for the Detection of Extended Radio Galaxies and Infrared Hosts

3 code implementations1 Dec 2023 Nikhel Gupta, Zeeshan Hayder, Ray P. Norris, Minh Huynh, Lars Petersson

Creating radio galaxy catalogues from next-generation deep surveys requires automated identification of associated components of extended sources and their corresponding infrared hosts.

object-detection Object Detection +1

Hyperbolic Audio-visual Zero-shot Learning

no code implementations ICCV 2023 Jie Hong, Zeeshan Hayder, Junlin Han, Pengfei Fang, Mehrtash Harandi, Lars Petersson

Audio-visual zero-shot learning aims to classify samples consisting of a pair of corresponding audio and video sequences from classes that are not present during training.

GZSL Video Classification

Deep Learning for Morphological Identification of Extended Radio Galaxies using Weak Labels

1 code implementation9 Aug 2023 Nikhel Gupta, Zeeshan Hayder, Ray P. Norris, Minh Huynh, Lars Petersson, X. Rosalind Wang, Heinz Andernach, Bärbel S. Koribalski, Miranda Yew, Evan J. Crawford

The CAMs are further refined using an inter-pixel relations network (IRNet) to get instance segmentation masks over radio galaxies and the positions of their infrared hosts.

Instance Segmentation Pathfinder +1

Automatic Illumination Spectrum Recovery

no code implementations31 May 2023 Nariman Habili, Jeremy Oorloff, Lars Petersson

We develop a deep learning network to estimate the illumination spectrum of hyperspectral images under various lighting conditions.

CVB: A Video Dataset of Cattle Visual Behaviors

no code implementations26 May 2023 Ali Zia, Renuka Sharma, Reza Arablouei, Greg Bishop-hurley, Jody McNally, Neil Bagnall, Vivien Rolland, Brano Kusy, Lars Petersson, Aaron Ingham

Therefore, we introduce a new dataset, called Cattle Visual Behaviors (CVB), that consists of 502 video clips, each fifteen seconds long, captured in natural lighting conditions, and annotated with eleven visually perceptible behaviors of grazing cattle.

Action Recognition

Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey

1 code implementation8 May 2023 Abdelwahed Khamis, Russell Tsuchida, Mohamed Tarek, Vivien Rolland, Lars Petersson

This paper is about where and how optimal transport is used in machine learning with a focus on the question of scalable optimal transport.

Topological Deep Learning: A Review of an Emerging Paradigm

no code implementations8 Feb 2023 Ali Zia, Abdelwahed Khamis, James Nichols, Zeeshan Hayder, Vivien Rolland, Lars Petersson

The summaries obtained by these methods are principled global descriptions of multi-dimensional data whilst exhibiting stable properties such as robustness to deformation and noise.

Topological Data Analysis

A Hyperspectral and RGB Dataset for Building Facade Segmentation

no code implementations6 Dec 2022 Nariman Habili, Ernest Kwan, Weihao Li, Christfried Webers, Jeremy Oorloff, Mohammad Ali Armin, Lars Petersson

Hyperspectral Imaging (HSI) provides detailed spectral information and has been utilised in many real-world applications.

Semantic Segmentation

PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning

1 code implementation5 Dec 2022 Jie Hong, Shi Qiu, Weihao Li, Saeed Anwar, Mehrtash Harandi, Nick Barnes, Lars Petersson

Specifically, we use the Unknown-Point Simulator to simulate out-of-distribution data in the training stage by manipulating the geometric context of partial known data.

What Images are More Memorable to Machines?

1 code implementation14 Nov 2022 Junlin Han, Huangying Zhan, Jie Hong, Pengfei Fang, Hongdong Li, Lars Petersson, Ian Reid

This paper studies the problem of measuring and predicting how memorable an image is to pattern recognition machines, as a path to explore machine intelligence.

Learning Deep Optimal Embeddings with Sinkhorn Divergences

no code implementations14 Sep 2022 Soumava Kumar Roy, Yan Han, Mehrtash Harandi, Lars Petersson

Deep Metric Learning algorithms aim to learn an efficient embedding space to preserve the similarity relationships among the input data.

Fine-Grained Image Recognition Image Classification +1

Curved Geometric Networks for Visual Anomaly Recognition

no code implementations2 Aug 2022 Jie Hong, Pengfei Fang, Weihao Li, Junlin Han, Lars Petersson, Mehrtash Harandi

Learning a latent embedding to understand the underlying nature of data distribution is often formulated in Euclidean spaces with zero curvature.

Anomaly Detection Out of Distribution (OOD) Detection +1

CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping

1 code implementation31 May 2022 Junlin Han, Lars Petersson, Hongdong Li, Ian Reid

We present a simple method, CropMix, for the purpose of producing a rich input distribution from the original dataset distribution.

Contrastive Learning

Monitoring of Pigmented Skin Lesions Using 3D Whole Body Imaging

no code implementations14 May 2022 David Ahmedt-Aristizabal, Chuong Nguyen, Lachlan Tychsen-Smith, Ashley Stacey, Shenghong Li, Joseph Pathikulangara, Lars Petersson, Dadong Wang

A modular camera rig arranged in a cylindrical configuration was designed to automatically capture images of the entire skin surface of a subject synchronously from multiple angles.

Image Reconstruction Lesion Detection +1

Pyramidal Attention for Saliency Detection

1 code implementation14 Apr 2022 Tanveer Hussain, Abbas Anwar, Saeed Anwar, Lars Petersson, Sung Wook Baik

Consequently, we present a new SOD perspective of generating RGB-D SOD without acquiring depth data during training and testing and assist RGB methods with depth clues for improved performance.

object-detection Object Detection +2

Towards Open-Set Object Detection and Discovery

no code implementations12 Apr 2022 Jiyang Zheng, Weihao Li, Jie Hong, Lars Petersson, Nick Barnes

This new task aims to extend the ability of open-set object detectors to further discover the categories of unknown objects based on their visual appearance without human effort.

Incremental Learning Object +2

Learning Dense Correspondence from Synthetic Environments

no code implementations24 Mar 2022 Mithun Lal, Anthony Paproki, Nariman Habili, Lars Petersson, Olivier Salvado, Clinton Fookes

Results show that training 2D-3D mapping network models on synthetic data is a viable alternative to using real data.

GOSS: Towards Generalized Open-set Semantic Segmentation

no code implementations23 Mar 2022 Jie Hong, Weihao Li, Junlin Han, Jiyang Zheng, Pengfei Fang, Mehrtash Harandi, Lars Petersson

In this paper, we present and study a new image segmentation task, called Generalized Open-set Semantic Segmentation (GOSS).

Clustering Image Segmentation +2

Continuous Human Action Recognition for Human-Machine Interaction: A Review

no code implementations26 Feb 2022 Harshala Gammulle, David Ahmedt-Aristizabal, Simon Denman, Lachlan Tychsen-Smith, Lars Petersson, Clinton Fookes

With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams.

Action Recognition Action Segmentation +4

Transcribing Natural Languages for The Deaf via Neural Editing Programs

1 code implementation17 Dec 2021 Dongxu Li, Chenchen Xu, Liu Liu, Yiran Zhong, Rong Wang, Lars Petersson, Hongdong Li

This work studies the task of glossification, of which the aim is to em transcribe natural spoken language sentences for the Deaf (hard-of-hearing) community to ordered sign language glosses.

Sentence

Towards a Robust Differentiable Architecture Search under Label Noise

no code implementations23 Oct 2021 Christian Simon, Piotr Koniusz, Lars Petersson, Yan Han, Mehrtash Harandi

Our empirical evaluations show that the noise injecting operation does not degrade the performance of the NAS algorithm if the data is indeed clean.

Neural Architecture Search

Declarative nets that are equilibrium models

no code implementations ICLR 2022 Russell Tsuchida, Suk Yee Yong, Mohammad Ali Armin, Lars Petersson, Cheng Soon Ong

We show that using a kernelised generalised linear model (kGLM) as an inner problem in a DDN yields a large class of commonly used DEQ architectures with a closed-form expression for the hidden layer parameters in terms of the kernel.

Feature Correlation Aggregation: on the Path to Better Graph Neural Networks

no code implementations20 Sep 2021 Jieming Zhou, Tong Zhang, Pengfei Fang, Lars Petersson, Mehrtash Harandi

The core concept of GNNs is to find a representation by recursively aggregating the representations of a central node and those of its neighbors.

Feature Correlation

Blind Image Decomposition

1 code implementation25 Aug 2021 Junlin Han, Weihao Li, Pengfei Fang, Chunyi Sun, Jie Hong, Mohammad Ali Armin, Lars Petersson, Hongdong Li

We propose and study a novel task named Blind Image Decomposition (BID), which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components involved in mixing as well as the mixing mechanism are unknown.

Rain Removal

A Survey on Graph-Based Deep Learning for Computational Histopathology

no code implementations1 Jul 2021 David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson

With the remarkable success of representation learning for prediction problems, we have witnessed a rapid expansion of the use of machine learning and deep learning for the analysis of digital pathology and biopsy image patches.

graph construction Image Retrieval +4

Towards Interpretable Attention Networks for Cervical Cancer Analysis

no code implementations27 May 2021 Ruiqi Wang, Mohammad Ali Armin, Simon Denman, Lars Petersson, David Ahmedt-Aristizabal

Here, we evaluate various state-of-the-art deep learning models and attention-based frameworks for the classification of images of multiple cervical cells.

Classification

Dual Contrastive Learning for Unsupervised Image-to-Image Translation

3 code implementations15 Apr 2021 Junlin Han, Mehrdad Shoeiby, Lars Petersson, Mohammad Ali Armin

Unsupervised image-to-image translation tasks aim to find a mapping between a source domain X and a target domain Y from unpaired training data.

Contrastive Learning Translation +1

Zero-Shot Learning on 3D Point Cloud Objects and Beyond

1 code implementation11 Apr 2021 Ali Cheraghian, Shafinn Rahman, Townim F. Chowdhury, Dylan Campbell, Lars Petersson

Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification.

3D Point Cloud Classification Classification +5

Reinforced Attention for Few-Shot Learning and Beyond

no code implementations CVPR 2021 Jie Hong, Pengfei Fang, Weihao Li, Tong Zhang, Christian Simon, Mehrtash Harandi, Lars Petersson

Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images.

Few-Shot Learning Image Classification

Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning

no code implementations CVPR 2021 Ali Cheraghian, Shafin Rahman, Pengfei Fang, Soumava Kumar Roy, Lars Petersson, Mehrtash Harandi

Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner.

Few-Shot Class-Incremental Learning Incremental Learning +2

Kernel Methods in Hyperbolic Spaces

no code implementations ICCV 2021 Pengfei Fang, Mehrtash Harandi, Lars Petersson

However, working in hyperbolic spaces is not without difficulties as a result of its curved geometry (e. g., computing the Frechet mean of a set of points requires an iterative algorithm).

Few-Shot Learning Image Classification +5

Set Augmented Triplet Loss for Video Person Re-Identification

no code implementations2 Nov 2020 Pengfei Fang, Pan Ji, Lars Petersson, Mehrtash Harandi

Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss.

Metric Learning Video-Based Person Re-Identification

Channel Recurrent Attention Networks for Video Pedestrian Retrieval

no code implementations7 Oct 2020 Pengfei Fang, Pan Ji, Jieming Zhou, Lars Petersson, Mehrtash Harandi

Full attention, which generates an attention value per element of the input feature maps, has been successfully demonstrated to be beneficial in visual tasks.

Person Retrieval Retrieval

Cross-Correlated Attention Networks for Person Re-Identification

no code implementations17 Jun 2020 Jieming Zhou, Soumava Kumar Roy, Pengfei Fang, Mehrtash Harandi, Lars Petersson

Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations -- to name a few -- when the task of person re-identification is considered.

Person Re-Identification

Attention Based Real Image Restoration

no code implementations26 Apr 2020 Saeed Anwar, Nick Barnes, Lars Petersson

Furthermore, the evaluation in terms of quantitative metrics and visual quality for four restoration tasks i. e. Denoising, Super-resolution, Raindrop Removal, and JPEG Compression on 11 real degraded datasets against more than 30 state-of-the-art algorithms demonstrate the superiority of our R$^2$Net.

Denoising Image Restoration +2

Mosaic Super-resolution via Sequential Feature Pyramid Networks

no code implementations15 Apr 2020 Mehrdad Shoeiby, Mohammad Ali Armin, Sadegh Aliakbarian, Saeed Anwar, Lars Petersson

Additionally, to the best of our knowledge, our method is the first specialized method to super-resolve mosaic images, whether it be multi-spectral or Bayer.

Astronomy Autonomous Driving +1

A Systematic Evaluation: Fine-Grained CNN vs. Traditional CNN Classifiers

1 code implementation24 Mar 2020 Saeed Anwar, Nick Barnes, Lars Petersson

In this work, we investigate the performance of the landmark general CNN classifiers, which presented top-notch results on large scale classification datasets, on the fine-grained datasets, and compare it against state-of-the-art fine-grained classifiers.

General Classification

Transferring Cross-domain Knowledge for Video Sign Language Recognition

no code implementations CVPR 2020 Dongxu Li, Xin Yu, Chenchen Xu, Lars Petersson, Hongdong Li

To this end, we extract news signs using a base WSLR model, and then design a classifier jointly trained on news and isolated signs to coarsely align these two domain features.

Sign Language Recognition

Contextually Plausible and Diverse 3D Human Motion Prediction

no code implementations ICCV 2021 Sadegh Aliakbarian, Fatemeh Sadat Saleh, Lars Petersson, Stephen Gould, Mathieu Salzmann

We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses.

Human motion prediction Image Captioning +1

Transductive Zero-Shot Learning for 3D Point Cloud Classification

1 code implementation16 Dec 2019 Ali Cheraghian, Shafin Rahman, Dylan Campbell, Lars Petersson

This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification.

3D Point Cloud Classification Classification +4

Neural Memory Networks for Seizure Type Classification

no code implementations10 Dec 2019 David Ahmedt-Aristizabal, Tharindu Fernando, Simon Denman, Lars Petersson, Matthew J. Aburn, Clinton Fookes

Inspired by recent advances in neural memory networks (NMNs), we introduce a novel approach for the classification of seizure type using electrophysiological data.

Classification EEG +4

Multi-FAN: Multi-Spectral Mosaic Super-Resolution Via Multi-Scale Feature Aggregation Network

no code implementations17 Sep 2019 Mehrdad Shoeiby, Sadegh Aliakbarian, Saeed Anwar, Lars Petersson

This mosaic image is then merged with the mosaic image generated by the SR network to produce a quantitatively superior image.

Super-Resolution

Super-resolved Chromatic Mapping of Snapshot Mosaic Image Sensors via a Texture Sensitive Residual Network

no code implementations5 Sep 2019 Mehrdad Shoeiby, Lars Petersson, Mohammad Ali Armin, Sadegh Aliakbarian, Antonio Robles-Kelly

This paper introduces a novel method to simultaneously super-resolve and colour-predict images acquired by snapshot mosaic sensors.

Learning Variations in Human Motion via Mix-and-Match Perturbation

no code implementations2 Aug 2019 Mohammad Sadegh Aliakbarian, Fatemeh Sadat Saleh, Mathieu Salzmann, Lars Petersson, Stephen Gould, Amirhossein Habibian

In this paper, we introduce an approach to stochastically combine the root of variations with previous pose information, which forces the model to take the noise into account.

Human motion prediction motion prediction

Zero-shot Learning of 3D Point Cloud Objects

1 code implementation27 Feb 2019 Ali Cheraghian, Shafin Rahman, Lars Petersson

A challenge for a 3D point cloud recognition system is, then, to classify objects from new, unseen, classes.

Attribute Zero-Shot Learning

The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation

no code implementations CVPR 2019 Dylan Campbell, Lars Petersson, Laurent Kneip, Hongdong Li, Stephen Gould

Determining the position and orientation of a calibrated camera from a single image with respect to a 3D model is an essential task for many applications.

Pose Estimation

3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds

no code implementations6 Nov 2018 Ali Cheraghian, Lars Petersson

This paper introduces the 3DCapsule, which is a 3D extension of the recently introduced Capsule concept that makes it applicable to unordered point sets.

Classification Classify 3D Point Clouds +1

Effective Use of Synthetic Data for Urban Scene Semantic Segmentation

no code implementations ECCV 2018 Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M. Alvarez

Our approach builds on the observation that foreground and background classes are not affected in the same manner by the domain shift, and thus should be treated differently.

Domain Adaptation Semantic Segmentation

Improving Object Localization with Fitness NMS and Bounded IoU Loss

1 code implementation CVPR 2018 Lachlan Tychsen-Smith, Lars Petersson

We demonstrate that many detection methods are designed to identify only a sufficently accurate bounding box, rather than the best available one.

Clustering Object Localization

Soft Correspondences in Multimodal Scene Parsing

no code implementations28 Sep 2017 Sarah Taghavi Namin, Mohammad Najafi, Mathieu Salzmann, Lars Petersson

We propose to address this issue, by formulating multimodal semantic labeling as inference in a CRF and introducing latent nodes to explicitly model inconsistencies between two modalities.

Scene Parsing

Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence

no code implementations ICCV 2017 Dylan Campbell, Lars Petersson, Laurent Kneip, Hongdong Li

Estimating the 6-DoF pose of a camera from a single image relative to a pre-computed 3D point-set is an important task for many computer vision applications.

Pose Estimation

Bringing Background into the Foreground: Making All Classes Equal in Weakly-supervised Video Semantic Segmentation

no code implementations ICCV 2017 Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M. Alvarez

Our experiments demonstrate the benefits of our classifier heatmaps and of our two-stream architecture on challenging urban scene datasets and on the YouTube-Objects benchmark, where we obtain state-of-the-art results.

Autonomous Navigation Segmentation +3

Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation

no code implementations6 Jun 2017 Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M. Alvarez, Stephen Gould

We then show how to obtain multi-class masks by the fusion of foreground/background ones with information extracted from a weakly-supervised localization network.

Object Recognition Segmentation +3

DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling

1 code implementation ICCV 2017 Lachlan Tychsen-Smith, Lars Petersson

Subsequently we identify a sparse distribution estimation scheme, Directed Sparse Sampling, and employ it in a single end-to-end CNN based detection model.

object-detection Object Localization +1

Encouraging LSTMs to Anticipate Actions Very Early

1 code implementation ICCV 2017 Mohammad Sadegh Aliakbarian, Fatemeh Sadat Saleh, Mathieu Salzmann, Basura Fernando, Lars Petersson, Lars Andersson

In contrast to the widely studied problem of recognizing an action given a complete sequence, action anticipation aims to identify the action from only partially available videos.

Action Anticipation Autonomous Navigation

DecomposeMe: Simplifying ConvNets for End-to-End Learning

no code implementations17 Jun 2016 Jose Alvarez, Lars Petersson

Deep learning and convolutional neural networks (ConvNets) have been successfully applied to most relevant tasks in the computer vision community.

GOGMA: Globally-Optimal Gaussian Mixture Alignment

no code implementations CVPR 2016 Dylan Campbell, Lars Petersson

Gaussian mixture alignment is a family of approaches that are frequently used for robustly solving the point-set registration problem.

Cutting Edge: Soft Correspondences in Multimodal Scene Parsing

no code implementations ICCV 2015 Sarah Taghavi Namin, Mohammad Najafi, Mathieu Salzmann, Lars Petersson

In this paper, we address the problem of data misalignment and label inconsistencies, e. g., due to moving objects, in semantic labeling, which violate the assumption of existing techniques.

Scene Parsing

Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering

no code implementations CVPR 2016 Mohammad Najafi, Sarah Taghavi Namin, Mathieu Salzmann, Lars Petersson

By contrast, nonparametric approaches, which bypass any learning phase and directly transfer the labels from the training data to the query images, can readily exploit new labeled samples as they become available.

Scene Parsing Superpixels

An Adaptive Data Representation for Robust Point-Set Registration and Merging

1 code implementation ICCV 2015 Dylan Campbell, Lars Petersson

This paper presents a framework for rigid point-set registration and merging using a robust continuous data representation.

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