Author name cluster

Gustavo Carneiro

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

1 author row

AAAI Conference 2026 Conference Paper

Coverage-Constrained Human-AI Cooperation with Multiple Experts

Zheng Zhang
Cuong C. Nguyen
Kevin Wells
Thanh-Toan Do
David Rosewarne
Gustavo Carneiro

Human-AI cooperative classification (HAI-CC) aims to develop hybrid intelligent systems that enhance decision-making in various high-stakes real-world scenarios by leveraging both human expertise and AI capabilities. Current HAI-CC methods primarily focus on learning-to-defer (L2D), where decisions are deferred to human experts when AI is not confident, and learning-to-complement (L2C), where AI and human experts make predictions cooperatively. However, existing research in both L2D and L2C has not effectively been explored under diverse expert knowledge to improve decision-making, particularly when constrained by the operation cost of human involvement. In this paper, we address this research gap by proposing the Coverage-constrained Learning to Defer and Complement with Specific Experts (CL2DC) method. In particular, CL2DC assesses input data before making final decisions through either AI prediction alone or by deferring to or complementing a specific human expert. Furthermore, we propose a coverage-constrained optimisation to control the cooperation cost, ensuring it approximates a target probability for AI-only selection. This approach enables an effective assessment of system performance within a specified budget. Comprehensive evaluations on both synthetic and real-world datasets demonstrate that CL2DC achieves superior performance compared to state-of-the-art HAI-CC methods.

PDF Details DOI

TMLR Journal 2026 Journal Article

Deep Multimodal Learning with Missing Modality: A Survey

Renjie Wu
Hu Wang
Hsiang-Ting Chen
Gustavo Carneiro

During multimodal model training and testing, certain data modalities may be absent due to sensor limitations, cost constraints, privacy concerns, or data loss, which can degrade performance. Multimodal learning techniques that explicitly account for missing modalities aim to improve robustness by enabling models to perform reliably even when certain inputs are unavailable. This survey presents the first comprehensive review of Multimodal Learning with Missing Modality (MLMM), with a focus on deep learning approaches. We outline the motivations and key distinctions between MLMM and conventional multimodal learning, provide a detailed analysis of existing methods, applications, and datasets, and conclude by highlighting open challenges and future research directions.

PDF Details

TMLR Journal 2025 Journal Article

Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learning

Hoang Anh Dung
Cuong C. Nguyen
Vasileios Belagiannis
Thanh-Toan Do
Gustavo Carneiro

Meta-learning is an effective method to handle imbalanced and noisy-label learning, but it generally depends on a clean validation set. Unfortunately, this validation set has poor scalability when the number of classes increases, as traditionally these samples need to be randomly selected, manually labelled and balanced-distributed. This problem therefore has motivated the development of meta-learning methods to automatically select validation samples that are likely to have clean labels and balanced class distribution. Unfortunately, a common missing point of existing meta-learning methods for noisy label learning is the lack of consideration for data informativeness when constructing the validation set. The construction of an informative validation set requires hard samples, i.e., samples that the model has low confident prediction, but these samples are more likely to be noisy, which can degrade the meta reweighting process. Therefore, the balance between sample informativeness and cleanness is an important criteria for validation set optimization. In this paper, we propose new criteria to characterise the utility of such meta-learning validation sets, based on: 1) sample informativeness; 2) balanced class distribution; and 3) label cleanliness. We also introduce a new imbalanced noisy-label meta-learning (INOLML) algorithm that auto- matically builds a validation set by maximising such utility criteria. The proposed method shows state-of-the-art (SOTA) results compared to previous meta-learning and noisy-label learning approaches on several noisy-label learning benchmarks.

PDF Details

JBHI Journal 2025 Journal Article

Progressive Mining and Dynamic Distillation of Hierarchical Prototypes for Disease Classification and Localisation

Chong Wang
Fengbei Liu
Yuanhong Chen
Chun Fung Kwok
Michael Elliott
Carlos Peña-Solorzano
Davis James McCarthy
Helen Frazer

Constructing effective representation of lesions is essential for disease classification and localization in medical image analysis. Prototype-based models address this by leveraging visual prototypes to capture representative lesion patterns, yet effectively handling the complexity of diverse lesion characteristics remains a critical challenge, as they typically rely on single-level, fixed-size prototypes and suffer from prototype redundancy. In this paper, we present HierProtoPNet, a new prototype-based framework designed to handle the complexity of lesions in medical images. HierProtoPNet leverages hierarchical visual prototypes across different semantic feature granularities to effectively capture diverse lesion patterns. To prevent redundancy and increase utility of the prototypes, we devise a novel prototype mining paradigm to progressively discover semantically distinct prototypes, offering multi-level complementary analysis of lesions. Also, we introduce a dynamic knowledge distillation strategy that allows transferring essential classification information across hierarchical levels, thereby improving generalisation performance. Comprehensive experiments show that HierProtoPNet achieves state-of-the-art classification performances in three benchmarks: binary breast cancer screening, multi-class retinal disease diagnosis, and multi-label chest X-ray classification. Quantitative assessments also illustrate HierProtoPNet's significant advantages in weakly-supervised disease localisation and segmentation.

Details DOI

NeurIPS Conference 2023 Conference Paper

Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning

Van Cuong Pham
Cuong Nguyen
Trung Le
Dinh Phung
Gustavo Carneiro
Thanh-Toan Do

Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared to deterministic neural networks. Utilizing mutual learning can effectively enhance the performance of peer BNNs. In this paper, we propose a novel approach to improve BNNs performance through deep mutual learning. The proposed approaches aim to increase diversity in both network parameter distributions and feature distributions, promoting peer networks to acquire distinct features that capture different characteristics of the input, which enhances the effectiveness of mutual learning. Experimental results demonstrate significant improvements in the classification accuracy, negative log-likelihood, and expected calibration error when compared to traditional mutual learning for BNNs.

PDF Details

TMLR Journal 2023 Journal Article

Task Weighting in Meta-learning with Trajectory Optimisation

Cuong C. 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 solutions. In this paper, we introduce a new principled and fully-automated task-weighting algorithm for meta-learning methods. By considering the weights of tasks within the same mini-batch as an action, and the meta-parameter of interest as the system state, we cast the task-weighting meta-learning problem to a trajectory optimisation and employ the iterative linear quadratic regulator to determine the optimal action or weights of tasks. We theoretically show that the proposed algorithm converges to an $\epsilon_{0}$-stationary point, and empirically demonstrate that the proposed approach out-performs common hand-engineering weighting methods in two few-shot learning benchmarks.

PDF Details

AAAI Conference 2022 Conference Paper

Deep One-Class Classification via Interpolated Gaussian Descriptor

Yuanhong Chen
Yu Tian
Guansong Pang
Gustavo Carneiro

One-class classification (OCC) aims to learn an effective data description to enclose all normal training samples and detect anomalies based on the deviation from the data description. Current state-of-the-art OCC models learn a compact normality description by hyper-sphere minimisation, but they often suffer from overfitting the training data, especially when the training set is small or contaminated with anomalous samples. To address this issue, we introduce the interpolated Gaussian descriptor (IGD) method, a novel OCC model that learns a one-class Gaussian anomaly classifier trained with adversarially interpolated training samples. The Gaussian anomaly classifier differentiates the training samples based on their distance to the Gaussian centre and the standard deviation of these distances, offering the model a discriminability w. r. t. the given samples during training. The adversarial interpolation is enforced to consistently learn a smooth Gaussian descriptor, even when the training data is small or contaminated with anomalous samples. This enables our model to learn the data description based on the representative normal samples rather than fringe or anomalous samples, resulting in significantly improved normality description. In extensive experiments on diverse popular benchmarks, including MNIST, Fashion MNIST, CIFAR10, MVTec AD and two medical datasets, IGD achieves better detection accuracy than current state-of-the-art models. IGD also shows better robustness in problems with small or contaminated training sets.

PDF Details

AIIM Journal 2021 Journal Article

Artificial intelligence for the diagnosis of lymph node metastases in patients with abdominopelvic malignancy: A systematic review and meta-analysis

Sergei Bedrikovetski
Nagendra N. Dudi-Venkata
Gabriel Maicas
Hidde M. Kroon
Warren Seow
Gustavo Carneiro
James W. Moore
Tarik Sammour

Purpose Accurate clinical diagnosis of lymph node metastases is of paramount importance in the treatment of patients with abdominopelvic malignancy. This review assesses the diagnostic performance of deep learning algorithms and radiomics models for lymph node metastases in abdominopelvic malignancies. Methodology Embase (PubMed, MEDLINE), Science Direct and IEEE Xplore databases were searched to identify eligible studies published between January 2009 and March 2019. Studies that reported on the accuracy of deep learning algorithms or radiomics models for abdominopelvic malignancy by CT or MRI were selected. Study characteristics and diagnostic measures were extracted. Estimates were pooled using random-effects meta-analysis. Evaluation of risk of bias was performed using the QUADAS-2 tool. Results In total, 498 potentially eligible studies were identified, of which 21 were included and 17 offered enough information for a quantitative analysis. Studies were heterogeneous and substantial risk of bias was found in 18 studies. Almost all studies employed radiomics models (n = 20). The single published deep-learning model out-performed radiomics models with a higher AUROC (0. 912 vs 0. 895), but both radiomics and deep-learning models outperformed the radiologist’s interpretation in isolation (0. 774). Pooled results for radiomics nomograms amongst tumour subtypes demonstrated the highest AUC 0. 895 (95 %CI, 0. 810−0. 980) for urological malignancy, and the lowest AUC 0. 798 (95 %CI, 0. 744−0. 852) for colorectal malignancy. Conclusion Radiomics models improve the diagnostic accuracy of lymph node staging for abdominopelvic malignancies in comparison with radiologist’s assessment. Deep learning models may further improve on this, but data remain limited.

Details DOI

AAAI Conference 2021 Short Paper

Domain Generalisation with Domain Augmented Supervised Contrastive Learning (Student Abstract)

Hoang Son Le
Rini Akmeliawati
Gustavo Carneiro

Domain generalisation (DG) methods address the problem of domain shift, when there is a mismatch between the distributions of training and target domains. Data augmentation approaches have emerged as a promising alternative for DG. However, data augmentation alone is not sufficient to achieve lower generalisation errors. This project proposes a new method that combines data augmentation and domain distance minimisation to address the problems associated with data augmentation and provide a guarantee on the learning performance, under an existing framework. Empirically, our method outperforms baseline results on DG benchmarks.

PDF Details

NeurIPS Conference 2017 Conference Paper

A Bayesian Data Augmentation Approach for Learning Deep Models

Toan Tran
Trung Pham
Gustavo Carneiro
Lyle Palmer
Ian Reid

Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be acquired, stored and processed. Therefore a reasonable alternative is to be able to automatically generate new annotated training samples using a process known as data augmentation. The dominant data augmentation approach in the field assumes that new training samples can be obtained via random geometric or appearance transformations applied to annotated training samples, but this is a strong assumption because it is unclear if this is a reliable generative model for producing new training samples. In this paper, we provide a novel Bayesian formulation to data augmentation, where new annotated training points are treated as missing variables and generated based on the distribution learned from the training set. For learning, we introduce a theoretically sound algorithm --- generalised Monte Carlo expectation maximisation, and demonstrate one possible implementation via an extension of the Generative Adversarial Network (GAN). Classification results on MNIST, CIFAR-10 and CIFAR-100 show the better performance of our proposed method compared to the current dominant data augmentation approach mentioned above --- the results also show that our approach produces better classification results than similar GAN models.

PDF Details

JBHI Journal 2017 Journal Article

Evaluation of Three Algorithms for the Segmentation of Overlapping Cervical Cells

Zhi Lu
Gustavo Carneiro
Andrew P. Bradley
Daniela Ushizima
Masoud S. Nosrati
Andrea G. C. Bianchi
Claudia M. Carneiro
Ghassan Hamarneh

In this paper, we introduce and evaluate the systems submitted to the first Overlapping Cervical Cytology Image Segmentation Challenge, held in conjunction with the IEEE International Symposium on Biomedical Imaging 2014. This challenge was organized to encourage the development and benchmarking of techniques capable of segmenting individual cells from overlapping cellular clumps in cervical cytology images, which is a prerequisite for the development of the next generation of computer-aided diagnosis systems for cervical cancer. In particular, these automated systems must detect and accurately segment both the nucleus and cytoplasm of each cell, even when they are clumped together and, hence, partially occluded. However, this is an unsolved problem due to the poor contrast of cytoplasm boundaries, the large variation in size and shape of cells, and the presence of debris and the large degree of cellular overlap. The challenge initially utilized a database of 16 high-resolution (×40 magnification) images of complex cellular fields of view, in which the isolated real cells were used to construct a database of 945 cervical cytology images synthesized with a varying number of cells and degree of overlap, in order to provide full access of the segmentation ground truth. These synthetic images were used to provide a reliable and comprehensive framework for quantitative evaluation on this segmentation problem. Results from the submitted methods demonstrate that all the methods are effective in the segmentation of clumps containing at most three cells, with overlap coefficients up to 0. 3. This highlights the intrinsic difficulty of this challenge and provides motivation for significant future improvement.

Details DOI