Search Results for author: Ales Leonardis

Found 52 papers, 12 papers with code

More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning

1 code implementation ECCV 2020 Yu Liu, Sarah Parisot, Gregory Slabaugh, Xu Jia, Ales Leonardis, Tinne Tuytelaars

Since those regularization strategies are mostly associated with classifier outputs, we propose a MUlti-Classifier (MUC) incremental learning paradigm that integrates an ensemble of auxiliary classifiers to estimate more effective regularization constraints.

Incremental Learning

Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representation

no code implementations9 Dec 2022 Wei Chen, Xi Jia, Zhongqun Zhang, Hyung Jin Chang, Linlin Shen, Ales Leonardis

The proposed rotation representation has two major advantages: 1) decoupled characteristic that makes the rotation estimation easier; 2) flexible length and rotated angle of the vectors allow us to find a more suitable vector representation for specific pose estimation task.

6D Pose Estimation using RGB Data Augmentation

Region Proposal Network Pre-Training Helps Label-Efficient Object Detection

no code implementations16 Nov 2022 Linus Ericsson, Nanqing Dong, Yongxin Yang, Ales Leonardis, Steven McDonagh

In this work, we propose a simple pretext task that provides an effective pre-training for the RPN, towards efficiently improving downstream object detection performance.

Instance Segmentation object-detection +3

Content-Diverse Comparisons improve IQA

no code implementations9 Nov 2022 William Thong, Jose Costa Pereira, Sarah Parisot, Ales Leonardis, Steven McDonagh

This restricts the diversity and number of image pairs that the model is exposed to during training.

Image Quality Assessment SSIM

Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment

no code implementations5 Aug 2022 Xue Hu, Xinghui Li, Benjamin Busam, Yiren Zhou, Ales Leonardis, Shanxin Yuan

Specifically, we focus on human appearance and learn implicit pose, shape and garment representations of dressed humans from RGB images.

3D Reconstruction Disentanglement

HDR Reconstruction from Bracketed Exposures and Events

no code implementations28 Mar 2022 Richard Shaw, Sibi Catley-Chandar, Ales Leonardis, Eduardo Perez-Pellitero

Our proposed approach surpasses SoTA multi-frame HDR reconstruction methods using synthetic and real events, with a 2dB and 1dB improvement in PSNR-L and PSNR-mu on the HdM HDR dataset, respectively.

HDR Reconstruction

Self-supervised HDR Imaging from Motion and Exposure Cues

no code implementations23 Mar 2022 Michal Nazarczuk, Sibi Catley-Chandar, Ales Leonardis, Eduardo Pérez Pellitero

Recent High Dynamic Range (HDR) techniques extend the capabilities of current cameras where scenes with a wide range of illumination can not be accurately captured with a single low-dynamic-range (LDR) image.

Wild ToFu: Improving Range and Quality of Indirect Time-of-Flight Depth with RGB Fusion in Challenging Environments

no code implementations7 Dec 2021 HyunJun Jung, Nikolas Brasch, Ales Leonardis, Nassir Navab, Benjamin Busam

Indirect Time-of-Flight (I-ToF) imaging is a widespread way of depth estimation for mobile devices due to its small size and affordable price.

Depth Estimation Depth Prediction

Depth-only Object Tracking

no code implementations22 Oct 2021 Song Yan, Jinyu Yang, Ales Leonardis, Joni-Kristian Kamarainen

There are two potential reasons for the heuristics: 1) the lack of large RGBD tracking datasets to train deep RGBD trackers and 2) the long-term evaluation protocol of VOT RGBD that benefits from heuristics such as depth-based occlusion detection.

Visual Object Tracking

Residual Contrastive Learning: Unsupervised Representation Learning from Residuals

no code implementations29 Sep 2021 Nanqing Dong, Matteo Maggioni, Yongxin Yang, Eduardo Pérez-Pellitero, Ales Leonardis, Steven McDonagh

In the era of deep learning, supervised residual learning (ResL) has led to many breakthroughs in low-level vision such as image restoration and enhancement tasks.

Contrastive Learning Image Reconstruction +3

Wavelet-Based Network For High Dynamic Range Imaging

no code implementations3 Aug 2021 Tianhong Dai, Wei Li, Xilei Cao, Jianzhuang Liu, Xu Jia, Ales Leonardis, Youliang Yan, Shanxin Yuan

The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details.

Optical Flow Estimation

Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images

no code implementations18 Jun 2021 Nanqing Dong, Matteo Maggioni, Yongxin Yang, Eduardo Pérez-Pellitero, Ales Leonardis, Steven McDonagh

We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), and derive an unsupervised visual representation learning framework, suitable for low-level vision tasks with noisy inputs.

Contrastive Learning Demosaicking +6

Learning a Model-Driven Variational Network for Deformable Image Registration

no code implementations25 May 2021 Xi Jia, Alexander Thorley, Wei Chen, Huaqi Qiu, Linlin Shen, Iain B Styles, Hyung Jin Chang, Ales Leonardis, Antonio de Marvao, Declan P. O'Regan, Daniel Rueckert, Jinming Duan

We then propose two neural layers (i. e. warping layer and intensity consistency layer) to model the analytical solution and a residual U-Net to formulate the denoising problem (i. e. generalized denoising layer).

Denoising Image Registration

DepthTrack: Unveiling the Power of RGBD Tracking

1 code implementation ICCV 2021 Song Yan, Jinyu Yang, Jani Kapyla, Feng Zheng, Ales Leonardis, Joni-Kristian Kamarainen

This can be explained by the fact that there are no sufficiently large RGBD datasets to 1) train "deep depth trackers" and to 2) challenge RGB trackers with sequences for which the depth cue is essential.

Object Tracking

Wavelet-Based Dual-Branch Network for Image Demoireing

no code implementations14 Jul 2020 Lin Liu, Jianzhuang Liu, Shanxin Yuan, Gregory Slabaugh, Ales Leonardis, Wengang Zhou, Qi Tian

When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality.

Image Restoration Rain Removal

Image Demoireing with Learnable Bandpass Filters

1 code implementation CVPR 2020 Bolun Zheng, Shanxin Yuan, Gregory Slabaugh, Ales Leonardis

Image demoireing is a multi-faceted image restoration task involving both texture and color restoration.

Ranked #2 on Image Enhancement on TIP 2018 (using extra training data)

Demoire Image Restoration +2

Unsupervised Model Personalization while Preserving Privacy and Scalability: An Open Problem

1 code implementation CVPR 2020 Matthias De Lange, Xu Jia, Sarah Parisot, Ales Leonardis, Gregory Slabaugh, Tinne Tuytelaars

This framework flexibly disentangles user-adaptation into model personalization on the server and local data regularization on the user device, with desirable properties regarding scalability and privacy constraints.

Continual Learning Domain Adaptation +2

G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features

1 code implementation CVPR 2020 Wei Chen, Xi Jia, Hyung Jin Chang, Jinming Duan, Ales Leonardis

Third, via the predicted segmentation and translation, we transfer the fine object point cloud into a local canonical coordinate, in which we train a rotation localization network to estimate initial object rotation.

6D Pose Estimation 6D Pose Estimation using RGB +1

A Multi-Hypothesis Approach to Color Constancy

1 code implementation CVPR 2020 Daniel Hernandez-Juarez, Sarah Parisot, Benjamin Busam, Ales Leonardis, Gregory Slabaugh, Steven McDonagh

Firstly, we select a set of candidate scene illuminants in a data-driven fashion and apply them to a target image to generate of set of corrected images.

Color Constancy

AIM 2019 Challenge on Image Demoireing: Dataset and Study

no code implementations6 Nov 2019 Shanxin Yuan, Radu Timofte, Gregory Slabaugh, Ales Leonardis

In addition to describing the dataset and its creation, this paper also reviews the challenge tracks, competition, and results, the latter summarizing the current state-of-the-art on this dataset.

Image Manipulation

A continual learning survey: Defying forgetting in classification tasks

1 code implementation18 Sep 2019 Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ales Leonardis, Gregory Slabaugh, Tinne Tuytelaars

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase.

Classification Continual Learning +2

Learning to Exploit Stability for 3D Scene Parsing

no code implementations NeurIPS 2018 Yilun Du, Zhijian Liu, Hector Basevi, Ales Leonardis, Bill Freeman, Josh Tenenbaum, Jiajun Wu

We first show that applying physics supervision to an existing scene understanding model increases performance, produces more stable predictions, and allows training to an equivalent performance level with fewer annotated training examples.

Scene Understanding Translation

Formulating Camera-Adaptive Color Constancy as a Few-shot Meta-Learning Problem

no code implementations28 Nov 2018 Steven McDonagh, Sarah Parisot, Fengwei Zhou, Xing Zhang, Ales Leonardis, Zhenguo Li, Gregory Slabaugh

In this work, we propose a new approach that affords fast adaptation to previously unseen cameras, and robustness to changes in capture device by leveraging annotated samples across different cameras and datasets.

Few-Shot Camera-Adaptive Color Constancy Meta-Learning

Exploring object-centric and scene-centric CNN features and their complementarity for human rights violations recognition in images

1 code implementation12 May 2018 Grigorios Kalliatakis, Shoaib Ehsan, Ales Leonardis, Klaus McDonald-Maier

With this, we show that HRA database poses a challenge at a higher level for the well studied representation learning methods, and provide a benchmark in the task of human rights violations recognition in visual context.

Representation Learning Transfer Learning

Material Classification in the Wild: Do Synthesized Training Data Generalise Better than Real-World Training Data?

no code implementations9 Nov 2017 Grigorios Kalliatakis, Anca Sticlaru, George Stamatiadis, Shoaib Ehsan, Ales Leonardis, Juergen Gall, Klaus D. McDonald-Maier

We question the dominant role of real-world training images in the field of material classification by investigating whether synthesized data can generalise more effectively than real-world data.

General Classification Material Classification

Rolling Shutter Correction in Manhattan World

no code implementations ICCV 2017 Pulak Purkait, Christopher Zach, Ales Leonardis

A vast majority of consumer cameras operate the rolling shutter mechanism, which often produces distorted images due to inter-row delay while capturing an image.

Performance Characterization of Image Feature Detectors in Relation to the Scene Content Utilizing a Large Image Database

no code implementations24 Sep 2017 Bruno Ferrarini, Shoaib Ehsan, Ales Leonardis, Naveed Ur Rehman, Klaus D. McDonald-Maier

Selecting the most suitable local invariant feature detector for a particular application has rendered the task of evaluating feature detectors a critical issue in vision research.

Detection of Human Rights Violations in Images: Can Convolutional Neural Networks help?

no code implementations12 Mar 2017 Grigorios Kalliatakis, Shoaib Ehsan, Maria Fasli, Ales Leonardis, Juergen Gall, Klaus D. McDonald-Maier

We conduct a rigorous evaluation on a common ground by combining this dataset with different state-of-the-art deep convolutional architectures in order to achieve recognition of human rights violations.

Semantic tracking: Single-target tracking with inter-supervised convolutional networks

no code implementations19 Nov 2016 Jingjing Xiao, Qiang Lan, Linbo Qiao, Ales Leonardis

Since each branch in NetT is trained by the videos of a specific category or groups of similar categories, NetT encodes category-based features for tracking.

General Classification

A Generic Framework for Assessing the Performance Bounds of Image Feature Detectors

no code implementations19 May 2016 Shoaib Ehsan, Adrian F. Clark, Ales Leonardis, Naveed Ur Rehman, Klaus D. McDonald-Maier

Since local feature detection has been one of the most active research areas in computer vision during the last decade, a large number of detectors have been proposed.

Automatic Selection of the Optimal Local Feature Detector

no code implementations19 May 2016 Bruno Ferrarini, Shoaib Ehsan, Naveed Ur Rehman, Ales Leonardis, Klaus D. McDonald-Maier

The efficiency and the good accuracy in determining the optimal feature detector for any operating condition, make the proposed tool suitable to be utilized in real visual applications.

Compositional Hierarchical Representation of Shape Manifolds for Classification of Non-Manifold Shapes

no code implementations ICCV 2015 Mete Ozay, Umit Rusen Aktas, Jeremy L. Wyatt, Ales Leonardis

We represent the topological relationship between shape components using graphs, which are aggregated to construct a hierarchical graph structure for the shape vocabulary.

General Classification

A Hierarchical Approach for Joint Multi-view Object Pose Estimation and Categorization

no code implementations4 Mar 2015 Mete Ozay, Krzysztof Walas, Ales Leonardis

We propose a joint object pose estimation and categorization approach which extracts information about object poses and categories from the object parts and compositions constructed at different layers of a hierarchical object representation algorithm, namely Learned Hierarchy of Parts (LHOP).

Distributed Optimization Object Categorization +1

A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid Generative-Descriptive Model

1 code implementation21 Jan 2015 Umit Rusen Aktas, Mete Ozay, Ales Leonardis, Jeremy L. Wyatt

A graph theoretic approach is proposed for object shape representation in a hierarchical compositional architecture called Compositional Hierarchy of Parts (CHOP).


Learning a Hierarchical Compositional Shape Vocabulary for Multi-class Object Representation

no code implementations23 Aug 2014 Sanja Fidler, Marko Boben, Ales Leonardis

At the top-level of the vocabulary, the compositions are sufficiently large and complex to represent the whole shapes of the objects.

Evaluating multi-class learning strategies in a generative hierarchical framework for object detection

no code implementations NeurIPS 2009 Sanja Fidler, Marko Boben, Ales Leonardis

We explore and compare their computational behavior (space and time) and detection performance as a function of the number of learned classes on several recognition data sets.

object-detection Object Detection

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