1.1k citations · 2.7k across the 92 of their papers we have counts for
99 papers
SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation
Youssef Dawoud, Gustavo Carneiro, Vasileios Belagiannis
Generalisation of deep neural networks becomes vulnerable when distribution shifts are encountered between train (source) and test (target) domain data. Few-shot domain adaptation…
Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation
Fengbei Liu, Chong Wang, Yuanhong Chen +2
Although noisy-label learning is often approached with discriminative methods for simplicity and speed, generative modeling offers a principled alternative by capturing the joint m…
Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling
Hu Wang, Yuanhong Chen, Congbo Ma +3
The missing modality issue is critical but non-trivial to be solved by multi-modal models. Current methods aiming to handle the missing modality problem in multi-modal tasks, eithe…
Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation
Arpit Garg, Cuong Nguyen, Rafael Felix +2
Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presen…
Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation
Yuanhong Chen, Yuyuan Liu, Hu Wang +4
Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. The effectiveness of audio-visual learning cr…
Multi-Head Multi-Loss Model Calibration
Adrian Galdran, Johan Verjans, Gustavo Carneiro +1
Delivering meaningful uncertainty estimates is essential for a successful deployment of machine learning models in the clinical practice. A central aspect of uncertainty quantifica…
PASS: Peer-Agreement based Sample Selection for training with Noisy Labels
Arpit Garg, Cuong Nguyen, Rafael Felix +2
The prevalence of noisy-label samples poses a significant challenge in deep learning, inducing overfitting effects. This has, therefore, motivated the emergence of learning with no…
AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challenge
Coen de Vente, Koenraad A. Vermeer, Nicolas Jaccard +33
The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effectiv…
Task Weighting in Meta-learning with Trajectory Optimisation
Cuong Nguyen, Thanh-Toan Do, Gustavo Carneiro
Developing meta-learning algorithms that are un-biased toward a subset of training tasks often requires hand-designed criteria to weight tasks, potentially resulting in sub-optimal…
Learning Support and Trivial Prototypes for Interpretable Image Classification
Chong Wang, Yuyuan Liu, Yuanhong Chen +5
Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable classification by associating predictions with a set of training prototypes, which we refe…
Asymmetric Co-teaching with Multi-view Consensus for Noisy Label Learning
Fengbei Liu, Yuanhong Chen, Chong Wang +2
Learning with noisy-labels has become an important research topic in computer vision where state-of-the-art (SOTA) methods explore: 1) prediction disagreement with co-teaching stra…
Knowing What to Label for Few Shot Microscopy Image Cell Segmentation
Youssef Dawoud, Arij Bouazizi, Katharina Ernst +2
In microscopy image cell segmentation, it is common to train a deep neural network on source data, containing different types of microscopy images, and then fine-tune it using a su…
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
Yuyuan Liu, Choubo Ding, Yu Tian +4
Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes. When deployed in an open world, the reliability of these models depends on th…
Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels
Brandon Smart, Gustavo Carneiro
Many state-of-the-art noisy-label learning methods rely on learning mechanisms that estimate the samples' clean labels during training and discard their original noisy labels. Howe…
Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation
Yuanhong Chen, Hu Wang, Chong Wang +6
When analysing screening mammograms, radiologists can naturally process information across two ipsilateral views of each breast, namely the cranio-caudal (CC) and mediolateral-obli…
On the Optimal Combination of Cross-Entropy and Soft Dice Losses for Lesion Segmentation with Out-of-Distribution Robustness
Adrian Galdran, Gustavo Carneiro, Miguel Ángel González Ballester
We study the impact of different loss functions on lesion segmentation from medical images. Although the Cross-Entropy (CE) loss is the most popular option when dealing with natura…
Instance-Dependent Noisy Label Learning via Graphical Modelling
Arpit Garg, Cuong Nguyen, Rafael Felix +2
Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because models can easily overfit them. There are many types of label noise, such as symmetric, asymm…
Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models
Chong Wang, Yuanhong Chen, Yuyuan Liu +6
State-of-the-art (SOTA) deep learning mammogram classifiers, trained with weakly-labelled images, often rely on global models that produce predictions with limited interpretability…
An Evolutionary Approach for Creating of Diverse Classifier Ensembles
Alvaro R. Ferreira, Fabio A. Faria, Gustavo Carneiro +1
Classification is one of the most studied tasks in data mining and machine learning areas and many works in the literature have been presented to solve classification problems for…
Edge-Based Self-Supervision for Semi-Supervised Few-Shot Microscopy Image Cell Segmentation
Youssef Dawoud, Katharina Ernst, Gustavo Carneiro +1
Deep neural networks currently deliver promising results for microscopy image cell segmentation, but they require large-scale labelled databases, which is a costly and time-consumi…
A Study on the Impact of Data Augmentation for Training Convolutional Neural Networks in the Presence of Noisy Labels
Emeson Santana, Gustavo Carneiro, Filipe R. Cordeiro
Label noise is common in large real-world datasets, and its presence harms the training process of deep neural networks. Although several works have focused on the training strateg…
Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learning
Dung Anh Hoang, Cuong Nguyen, Belagiannis Vasileios +2
Meta-learning is an effective method to handle imbalanced and noisy-label learning, but it depends on a validation set containing randomly selected, manually labelled and balanced…
Uncertainty-aware Multi-modal Learning via Cross-modal Random Network Prediction
Hu Wang, Jianpeng Zhang, Yuanhong Chen +4
Multi-modal learning focuses on training models by equally combining multiple input data modalities during the prediction process. However, this equal combination can be detrimenta…
Test Time Transform Prediction for Open Set Histopathological Image Recognition
Adrian Galdran, Katherine J. Hewitt, Narmin L. Ghaffari +3
Tissue typology annotation in Whole Slide histological images is a complex and tedious, yet necessary task for the development of computational pathology models. We propose to addr…