Gustavo Carneiro

Prof. Dr. Gustavo Carneiro

orcid

Research Focus & Metrics

Academic Career Length

28Years (1999-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 September 2016
Verified
Book Chapter
Closed access
PDF file
RGRavi Garg
Ravi Garg
VBVijay Kumar B.G.
Vijay Kumar B.G.
GCGustavo Carneiro
Gustavo Carneiro
IRIan Reid
Ian Reid

22 January 2007 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
GCGustavo Carneiro
Gustavo Carneiro
ACAntoni B. Chan
Antoni B. Chan
PMPedro J. Moreno
Pedro J. Moreno
NVNuno Vasconcelos
Nuno Vasconcelos
A probabilistic formulation for semantic image annotation and retrieval is proposed. Annotation and retrieval are posed as classification problems where each class is defined as the group of database images labeled with a common semantic label. It is shown that, by establishing this one-to-one correspondence between semantic labels and semantic classes, a minimum probability of error annotation and retrieval are feasible with algorithms that are 1) conceptually simple, 2) computationally efficient, and 3) do not require prior semantic segmentation of training images. In particular, images are represented as bags of localized feature vectors, a mixture density estimated for each image, and the mixtures associated with all images annotated with a common semantic label pooled into a density estimate for the corresponding semantic class. This pooling is justified by a multiple instance learning argument and performed efficiently with a hierarchical extension of expectation-maximization. The benefits of the supervised formulation over the more complex, and currently popular, joint modeling of semantic label and visual feature distributions are illustrated through theoretical arguments and extensive experiments. The supervised formulation is shown to achieve higher accuracy than various previously published methods at a fraction of their computational cost. Finally, the proposed method is shown to be fairly robust to parameter tuning

2 April 2020
Verified
Conference Paper
Open access
LOLuke Oakden-Rayner
Luke Oakden-Rayner
JDJared Dunnmon
Jared Dunnmon
GCGustavo Carneiro
Gustavo Carneiro
CRChristopher Re
Christopher Re
Machine learning models for medical image analysis often suffer from poor performance on important subsets of a population that are not identified during training or testing. For example, overall performance of a cancer detection model may be high, but the model may still consistently miss a rare but aggressive cancer subtype. We refer to this problem as hidden stratification, and observe that it results from incompletely describing the meaningful variation in a dataset. While hidden stratification can substantially reduce the clinical efficacy of machine learning models, its effects remain difficult to measure. In this work, we assess the utility of several possible techniques for measuring hidden stratification effects, and characterize these effects both via synthetic experiments on the CIFAR-100 benchmark dataset and on multiple real-world medical imaging datasets. Using these measurement techniques, we find evidence that hidden stratification can occur in unidentified imaging subsets with low prevalence, low label quality, subtle distinguishing features, or spurious correlates, and that it can result in relative performance differences of over 20% on clinically important subsets. Finally, we discuss the clinical implications of our findings, and suggest that evaluation of hidden stratification should be a critical component of any machine learning deployment in medical imaging.

1 April 2017 in Medical Image Analysis
Verified
Journal Article
Closed access
NDNeeraj Dhungel
Neeraj Dhungel
GCGustavo Carneiro
Gustavo Carneiro
ABAndrew Bradley
Andrew Bradley

1 January 2017 in Medical Image Analysis
Verified
Journal Article
Closed access
TNTuan Anh Ngo
Tuan Anh Ngo
ZLZhi Lu
Zhi Lu
GCGustavo Carneiro
Gustavo Carneiro

1 October 2017
Verified
Conference Paper
Closed access
BHBen Harwood
Ben Harwood
VBVijay Kumar B.G.
Vijay Kumar B.G.
GCGustavo Carneiro
Gustavo Carneiro
IRIan Reid
Ian Reid
TDTom Drummond
Tom Drummond
To solve deep metric learning problems and producing feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples from the same class and maximise the relative distance between samples from different classes. Though successful, the training convergence of this triplet model can be compromised by the fact that the vast majority of the training samples will produce gradients with magnitudes that are close to zero. This issue has motivated the development of methods that explore the global structure of the embedding and other methods that explore hard negative/positive mining. The effectiveness of such mining methods is often associated with intractable computational requirements. In this paper, we propose a novel deep metric learning method that combines the triplet model and the global structure of the embedding space. We rely on a smart mining procedure that produces effective training samples for a low computational cost. In addition, we propose an adaptive controller that automatically adjusts the smart mining hyper-parameters and speeds up the convergence of the training process. We show empirically that our proposed method allows for fast and more accurate training of triplet ConvNets than other competing mining methods. Additionally, we show that our method achieves new state-of-the-art embedding results for CUB-200-2011 and Cars196 datasets.