Search Results for author:
Found 130 papers, 62 papers with code
AI-Powered Prediction of Nanoparticle Pharmacokinetics: A Multi-View Learning Approach
The clinical translation of nanoparticle-based treatments remains limited due to the unpredictability of (nanoparticle) NP pharmacokinetics$\unicode{x2014}$how they distribute, accumulate, and clear from the body.
Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning
with the training data as a validation set to evaluate model performance and perform label correction in a meta learning framework, eliminating the need for extra clean data.
Leveraging Labelled Data Knowledge: A Cooperative Rectification Learning Network for Semi-supervised 3D Medical Image Segmentation
Semi-supervised 3D medical image segmentation aims to achieve accurate segmentation using few labelled data and numerous unlabelled data.
AEON: Adaptive Estimation of Instance-Dependent In-Distribution and Out-of-Distribution Label Noise for Robust Learning
Real-world datasets often contain a mix of in-distribution (ID) and out-of-distribution (OOD) instance-dependent label noise, a challenge that is rarely addressed simultaneously by existing methods and is further compounded by the lack of comprehensive benchmarking datasets.
Coverage-Constrained Human-AI Cooperation with Multiple Experts
However, a notable research gap remains in effectively exploring both L2D and L2C under diverse expert knowledge to improve decision-making, particularly when constrained by the cooperation cost required to achieve a target probability for AI-only selection (i. e., coverage).
Fair Distillation: Teaching Fairness from Biased Teachers in Medical Imaging
Deep learning has achieved remarkable success in image classification and segmentation tasks.
Rethinking Weight-Averaged Model-merging
Weight-averaged model-merging has emerged as a powerful approach in deep learning, capable of enhancing model performance without fine-tuning or retraining.
Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretation
Recent advances in prototypical learning have shown remarkable potential to provide useful decision interpretations associating activation maps and predictions with class-specific training prototypes.
ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labels
An important stage of most state-of-the-art (SOTA) noisy-label learning methods consists of a sample selection procedure that classifies samples from the noisy-label training set into noisy-label or clean-label subsets.
A Novel Perspective for Multi-modal Multi-label Skin Lesion Classification
The efficacy of deep learning-based Computer-Aided Diagnosis (CAD) methods for skin diseases relies on analyzing multiple data modalities (i. e., clinical+dermoscopic images, and patient metadata) and addressing the challenges of multi-label classification.
Deep Multimodal Learning with Missing Modality: A Survey
During multimodal model training and testing, certain data modalities may be absent due to sensor limitations, cost constraints, privacy concerns, or data loss, negatively affecting performance.
Human-AI Collaborative Multi-modal Multi-rater Learning for Endometriosis Diagnosis
HAICOMM is the first method that explores three important aspects of this problem: 1) multi-rater learning to extract a cleaner label from the multiple "noisy" labels available per training sample; 2) multi-modal learning to leverage the presence of T1/T2 MRI images for training and testing; and 3) human-AI collaboration to build a system that leverages the predictions from clinicians and the AI model to provide more accurate classification than standalone clinicians and AI models.
MetaAug: Meta-Data Augmentation for Post-Training Quantization
The transformation network modifies the original calibration data and the modified data will be used as the training set to learn the quantized model with the objective that the quantized model achieves a good performance on the original calibration data.
Bayesian Detector Combination for Object Detection with Crowdsourced Annotations
Most prior object detection methods assume accurate annotations; A few recent works have studied object detection with noisy crowdsourced annotations, with evaluation on distinct synthetic crowdsourced datasets of varying setups under artificial assumptions.
ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation
Additionally, these SSL approaches employ contrastive learning based on the sampling from a limited set of positive and negative embedding samples.
Learning to Complement and to Defer to Multiple Users
This process has three options: 1) AI autonomously classifies, 2) learning to complement, where AI collaborates with users, and 3) learning to defer, where AI defers to users.
CPM: Class-conditional Prompting Machine for Audio-visual Segmentation
However, the inherent training issues of transformer-based methods, such as the low efficacy of cross-attention and unstable bipartite matching, can be amplified in AVS, particularly when the learned audio query does not provide a clear semantic clue.
Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning
Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions.
Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation
In monocular depth estimation, unsupervised domain adaptation has recently been explored to relax the dependence on large annotated image-based depth datasets.
Meta-Learned Modality-Weighted Knowledge Distillation for Robust Multi-Modal Learning with Missing Data
In multi-modal learning, some modalities are more influential than others, and their absence can have a significant impact on classification/segmentation accuracy.
Frequency Attention for Knowledge Distillation
Inspired by the benefits of the frequency domain, we propose a novel module that functions as an attention mechanism in the frequency domain.
Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition
Existing methods, which rely on a point-based learning of prototypes, typically face two critical issues: 1) the learned prototypes have limited representation power and are not suitable to detect Out-of-Distribution (OoD) inputs, reducing their decision trustworthiness; and 2) the necessary projection of the learned prototypes back into the space of training images causes a drastic degradation in the predictive performance.
Learning to Complement with Multiple Humans
The ill-posedness of the LNL task requires the adoption of strong assumptions or the use of multiple noisy labels per training image, resulting in accurate models that work well in isolation but fail to optimise human-AI collaborative classification (HAI-CC).
Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality
Then, cross-modal knowledge distillation is performed between teacher and student modalities for each task to push the model parameters to a point that is beneficial for all tasks.
SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation
Few-shot domain adaptation mitigates this issue by adapting deep neural networks pre-trained on the source domain to the target domain using a randomly selected and annotated support set from the target domain.
Partial Label Supervision for Agnostic Generative Noisy Label Learning
Second, we introduce a new Partial Label Supervision (PLS) for noisy label learning that accounts for both clean label coverage and uncertainty.
Ranked #6 on
Learning with noisy labels
on CIFAR-10N-Random3
Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling
Current methods aiming to handle the missing modality problem in multi-modal tasks, either deal with missing modalities only during evaluation or train separate models to handle specific missing modality settings.
Distilling Missing Modality Knowledge from Ultrasound for Endometriosis Diagnosis with Magnetic Resonance Images
Next, we distill the knowledge from the teacher TVUS POD obliteration detector to train the student MRI model by minimizing a regression loss that approximates the output of the student to the teacher using unpaired TVUS and MRI data.
Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation
To address IDN, Label Noise Learning (LNL) incorporates a sample selection stage to differentiate clean and noisy-label samples.
Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation
We show empirical results that demonstrate the effectiveness of our benchmark.
PASS: Peer-Agreement based Sample Selection for training with Noisy Labels
The prevalence of noisy-label samples poses a significant challenge in deep learning, inducing overfitting effects.
Multi-Head Multi-Loss Model Calibration
Delivering meaningful uncertainty estimates is essential for a successful deployment of machine learning models in the clinical practice.
AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challenge
Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible.
BRAIxDet: Learning to Detect Malignant Breast Lesion with Incomplete Annotations
Given the large size of such datasets, researchers usually face a dilemma with the weakly annotated subset: to not use it or to fully annotate it.
Learning Support and Trivial Prototypes for Interpretable Image Classification
Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable classification by associating predictions with a set of training prototypes, which we refer to as trivial prototypes because they are trained to lie far from the classification boundary in the feature space.
Explainable Artificial Intelligence (XAI)
Image Classification
+1
Task Weighting in Meta-learning with Trajectory Optimisation
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.
Towards the Identifiability in Noisy Label Learning: A Multinomial Mixture Approach
To meet this requirement without relying on additional $2C - 2$ manual annotations per instance, we propose a method that automatically generates additional noisy labels by estimating the noisy label distribution based on nearest neighbours.
Asymmetric Co-teaching with Multi-view Consensus for Noisy Label Learning
Also, the new sample selection is based on multi-view consensus, which uses the label views from training labels and model predictions to divide the training set into clean and noisy for training the multi-class model and to re-label the training samples with multiple top-ranked labels for training the multi-label model.
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes.
Ranked #1 on
Anomaly Detection
on Fishyscapes
(using extra training data)
Knowing What to Label for Few Shot Microscopy Image Cell Segmentation
In this paper, we argue that the random selection of unlabelled training target images to be annotated and included in the support set may not enable an effective fine-tuning process, so we propose a new approach to optimise this image selection process.
Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels
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.
Ranked #4 on
Learning with noisy labels
on ANIMAL
Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models
On the other hand, prototype-based models improve interpretability by associating predictions with training image prototypes, but they are less accurate than global models and their prototypes tend to have poor diversity.
Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation
When analysing screening mammograms, radiologists can naturally process information across two ipsilateral views of each breast, namely the cranio-caudal (CC) and mediolateral-oblique (MLO) views.
On the Optimal Combination of Cross-Entropy and Soft Dice Losses for Lesion Segmentation with Out-of-Distribution Robustness
Our findings are surprising: CE-Dice loss combinations that excel in segmenting in-distribution images have a poor performance when dealing with OoD data, which leads us to recommend the adoption of the CE loss for this kind of problems, due to its robustness and ability to generalize to OoD samples.
Instance-Dependent Noisy Label Learning via Graphical Modelling
Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because models can easily overfit them.
Ranked #1 on
Learning with noisy labels
on CIFAR-100
An Evolutionary Approach for Creating of Diverse Classifier Ensembles
We address this point by proposing a framework for classifier selection and fusion based on a four-step protocol called CIF-E (Classifiers, Initialization, Fitness function, and Evolutionary algorithm).
A Study on the Impact of Data Augmentation for Training Convolutional Neural Networks in the Presence of Noisy Labels
Label noise is common in large real-world datasets, and its presence harms the training process of deep neural networks.
Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learning
In this paper, we analyse the meta-learning algorithm and propose new criteria to characterise the utility of the validation set, based on: 1) the informativeness of the validation set; 2) the class distribution balance of the set; and 3) the correctness of the labels of the set.
Edge-Based Self-Supervision for Semi-Supervised Few-Shot Microscopy Image Cell Segmentation
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-consuming process.
Uncertainty-aware Multi-modal Learning via Cross-modal Random Network Prediction
Multi-modal learning focuses on training models by equally combining multiple input data modalities during the prediction process.
Test Time Transform Prediction for Open Set Histopathological Image Recognition
In test time, we measure model confidence in predicting this transform, which we expect to be lower for images in the Open Set.
Censor-aware Semi-supervised Learning for Survival Time Prediction from Medical Images
In this work, we propose a new training method that predicts survival time using all censored and uncensored data.
Mixup-based Deep Metric Learning Approaches for Incomplete Supervision
Deep learning architectures have achieved promising results in different areas (e. g., medicine, agriculture, and security).
Translation Consistent Semi-supervised Segmentation for 3D Medical Images
The most successful SSL approaches are based on consistency learning that minimises the distance between model responses obtained from perturbed views of the unlabelled data.
Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection
Current polyp detection methods from colonoscopy videos use exclusively normal (i. e., healthy) training images, which i) ignore the importance of temporal information in consecutive video frames, and ii) lack knowledge about the polyps.
Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencoder
Our UAD approach, the memory-augmented multi-level cross-attentional masked autoencoder (MemMC-MAE), is a transformer-based approach, consisting of a novel memory-augmented self-attention operator for the encoder and a new multi-level cross-attention operator for the decoder.
BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification
Deep learning methods have shown outstanding classification accuracy in medical imaging problems, which is largely attributed to the availability of large-scale datasets manually annotated with clean labels.
In Defense of Kalman Filtering for Polyp Tracking from Colonoscopy Videos
We advocate that the field should instead focus on the development of simple and efficient detectors that an be combined with effective trackers to allow the implementation of real-time polyp detectors.
Mutual information neural estimation for unsupervised multi-modal registration of brain images
We propose guiding the training of a deep learning-based registration method with MI estimation between an image-pair in an end-to-end trainable network.
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image Classification
Effective semi-supervised learning (SSL) in medical image analysis (MIA) must address two challenges: 1) work effectively on both multi-class (e. g., lesion classification) and multi-label (e. g., multiple-disease diagnosis) problems, and 2) handle imbalanced learning (because of the high variance in disease prevalence).
Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
The accurate prediction by this model allows us to use a challenging combination of network, input data and feature perturbations to improve the consistency learning generalisation, where the feature perturbations consist of a new adversarial perturbation.
Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes
However, previous uncertainty approaches that directly associate high uncertainty to anomaly may sometimes lead to incorrect anomaly predictions, and external reconstruction models tend to be too inefficient for real-time self-driving embedded systems.
Ranked #2 on
Anomaly Detection
on Lost and Found
(using extra training data)
A Hierarchical Multi-Task Approach to Gastrointestinal Image Analysis
We also describe in this paper our solution for the challenge task of polyp segmentation in colonoscopies, which was addressed with a pretrained double encoder-decoder network.
Convolutional Nets Versus Vision Transformers for Diabetic Foot Ulcer Classification
This paper compares well-established Convolutional Neural Networks (CNNs) to recently introduced Vision Transformers for the task of Diabetic Foot Ulcer Classification, in the context of the DFUC 2021 Grand-Challenge, in which this work attained the first position.
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels
The most competitive noisy label learning methods rely on an unsupervised classification of clean and noisy samples, where samples classified as noisy are re-labelled and "MixMatched" with the clean samples.
Ranked #1 on
Image Classification with Label Noise
on CIFAR-100
Image Classification with Label Noise
Learning with noisy labels
Double Encoder-Decoder Networks for Gastrointestinal Polyp Segmentation
Polyps represent an early sign of the development of Colorectal Cancer.
Balanced-MixUp for Highly Imbalanced Medical Image Classification
The resulting two sets of samples are then mixed-up to create a more balanced training distribution from which a neural network can effectively learn without incurring in heavily under-fitting the minority classes.
Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Images
Pre-training UAD methods with self-supervised learning, based on computer vision techniques, can mitigate this challenge, but they are sub-optimal because they do not explore domain knowledge for designing the pretext tasks, and their contrastive learning losses do not try to cluster the normal training images, which may result in a sparse distribution of normal images that is ineffective for anomaly detection.
3D Semantic Mapping from Arthroscopy using Out-of-distribution Pose and Depth and In-distribution Segmentation Training
In this paper, we propose the first 3D semantic mapping system from knee arthroscopy that solves the three challenges above.
Probabilistic task modelling for meta-learning
We propose probabilistic task modelling -- a generative probabilistic model for collections of tasks used in meta-learning.
Self-supervised Lesion Change Detection and Localisation in Longitudinal Multiple Sclerosis Brain Imaging
Hence, we introduce a new unsupervised anomaly detection and localisation method trained exclusively with serial images that do not contain any lesion changes.
Kernel Adversarial Learning for Real-world Image Super-resolution
Current deep image super-resolution (SR) approaches aim to restore high-resolution images from down-sampled images or by assuming degradation from simple Gaussian kernels and additive noises.
ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning
We propose a new training algorithm, ScanMix, that explores semantic clustering and semi-supervised learning (SSL) to allow superior robustness to severe label noise and competitive robustness to non-severe label noise problems, in comparison to the state of the art (SOTA) methods.
Ranked #26 on
Image Classification
on mini WebVision 1.0
NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification
In this paper, we propose a new training module called Non-Volatile Unbiased Memory (NVUM), which non-volatility stores running average of model logits for a new regularization loss on noisy multi-label problem.
Image Classification with Label Noise
Learning with noisy labels
+2
LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment
Deep neural network models are robust to a limited amount of label noise, but their ability to memorise noisy labels in high noise rate problems is still an open issue.
Ranked #1 on
Learning with noisy labels
on Food-101
Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images
Unsupervised anomaly detection (UAD) learns one-class classifiers exclusively with normal (i. e., healthy) images to detect any abnormal (i. e., unhealthy) samples that do not conform to the expected normal patterns.
Ranked #1 on
Anomaly Detection
on LAG
Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification
In this paper, we propose Self-supervised Mean Teacher for Semi-supervised (S$^2$MTS$^2$) learning that combines self-supervised mean-teacher pre-training with semi-supervised fine-tuning.
Post-hoc Overall Survival Time Prediction from Brain MRI
In this paper, we introduce a new post-hoc method for OS time prediction that does not require segmentation map annotation for training.
Similarity of Classification Tasks
Recent advances in meta-learning has led to remarkable performances on several few-shot learning benchmarks.
Deep One-Class Classification via Interpolated Gaussian Descriptor
The adversarial interpolation is enforced to consistently learn a smooth Gaussian descriptor, even when the training data is small or contaminated with anomalous samples.
Ranked #2 on
Anomaly Detection
on MNIST
(using extra training data)
Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning
To address this issue, we introduce a novel and theoretically sound method, named Robust Temporal Feature Magnitude learning (RTFM), which trains a feature magnitude learning function to effectively recognise the positive instances, substantially improving the robustness of the MIL approach to the negative instances from abnormal videos.
Anomaly Detection In Surveillance Videos
Contrastive Learning
+2
Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning
In this paper, we propose and analyse a system that can automatically detect, localise and classify polyps from colonoscopy videos.
Semantics for Robotic Mapping, Perception and Interaction: A Survey
In robotics and related research fields, the study of understanding is often referred to as semantics, which dictates what does the world "mean" to a robot, and is strongly tied to the question of how to represent that meaning.
A Chaos Theory Approach to Understand Neural Network Optimization
Then, we empirically show that for a large range of learning rates, SGD traverses the loss landscape across regions with largest eigenvalue of the Hessian similar to the inverse of the learning rate.
Bayesian Metric Learning for Robust Training of Deep Models under Noisy Labels
Label noise is a natural event of data collection and annotation and has been shown to have significant impact on the performance of deep learning models regarding accuracy reduction and sample complexity increase.
Domain Generalisation with Domain Augmented Supervised Contrastive Learning (Student Abstract)
Domain generalisation (DG) methods address the problem of domain shift, when there is a mismatch between the distributions of training and target domains.
A Survey on Deep Learning with Noisy Labels: How to train your model when you cannot trust on the annotations?
As deep learning models depend on correctly labeled data sets and label correctness is difficult to guarantee, it is crucial to consider the presence of noisy labels for deep learning training.
EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels
In this work, we study a new variant of the noisy label problem that combines the open-set and closed-set noisy labels, and introduce a benchmark evaluation to assess the performance of training algorithms under this setup.
Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach for Feature Embedding
Based on pseudo labels, we propose a novel unsupervised metric loss which enforces the positive concentration and negative separation of samples in the embedding space.
Self-supervised Depth Estimation to Regularise Semantic Segmentation in Knee Arthroscopy
In this paper, we propose a novel self-supervised monocular depth estimation to regularise the training of the semantic segmentation in knee arthroscopy.
Few-Shot Microscopy Image Cell Segmentation
Instead, we assume that we can access a plethora of annotated image data sets from different domains (sources) and a limited number of annotated image data sets from the domain of interest (target), where each domain denotes not only different image appearance but also a different type of cell segmentation problem.
Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy
Anomaly detection methods generally target the learning of a normal image distribution (i. e., inliers showing healthy cases) and during testing, samples relatively far from the learned distribution are classified as anomalies (i. e., outliers showing disease cases).
Region Proposals for Saliency Map Refinement for Weakly-supervised Disease Localisation and Classification
The deployment of automated systems to diagnose diseases from medical images is challenged by the requirement to localise the diagnosed diseases to justify or explain the classification decision.
Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume
We show that the extension of the state-of-the-art self-supervised monocular trained depth estimator Monodepth2 with these two ideas allows us to design a model that produces the best results in the field in KITTI 2015 and Make3D, closing the gap with respect self-supervised stereo training and fully supervised approaches.
PAC-Bayes meta-learning with implicit task-specific posteriors
We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning.
Unsupervised Dual Adversarial Learning for Anomaly Detection in Colonoscopy Video Frames
We show that our proposed approach achieves the state-of-the-art result on this data set, compared with recently proposed anomaly detection systems.
Semi-supervised Multi-domain Multi-task Training for Metastatic Colon Lymph Node Diagnosis From Abdominal CT
However, the lack of annotations for the localisation of the regions of interest (ROIs) containing lymph nodes can limit classification accuracy due to the small size of the relevant ROIs in this problem.
Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging
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.
Generalised Zero-Shot Learning with Domain Classification in a Joint Semantic and Visual Space
Most state-of-the-art GZSL approaches rely on a mapping between latent visual and semantic spaces without considering if a particular sample belongs to the set of seen or unseen classes.
Generalised Zero-Shot Learning with a Classifier Ensemble over Multi-Modal Embedding Spaces
In the context of GZSL, semantic information is non-visual data such as a text description of both seen and unseen classes.
Few-Shot Meta-Denoising
A solution to mitigate the small training set issue is to pre-train a denoising model with small training sets containing pairs of clean and synthesized noisy signals, produced from empirical noise priors, and fine-tune on the available small training set.
Uncertainty in Model-Agnostic Meta-Learning using Variational Inference
We introduce a new, rigorously-formulated Bayesian meta-learning algorithm that learns a probability distribution of model parameter prior for few-shot learning.
Unsupervised Task Design to Meta-Train Medical Image Classifiers
Meta-training has been empirically demonstrated to be the most effective pre-training method for few-shot learning of medical image classifiers (i. e., classifiers modeled with small training sets).
Bayesian Generative Active Deep Learning
Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of problems that can be tackled.
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
Another approach explored in the field relies on an ad-hoc linearization (in terms of N) of the triplet loss that introduces class centroids, which must be optimized using the whole training set for each mini-batch - this means that a naive implementation of this approach has run-time complexity O(N^2).
Multi-modal Ensemble Classification for Generalized Zero Shot Learning
In this paper, we mitigate these issues by proposing a new GZSL method based on multi-modal training and testing processes, where the optimization explicitly promotes a balanced classification accuracy between seen and unseen classes.
Probabilistic Object Detection: Definition and Evaluation
We introduce Probabilistic Object Detection, the task of detecting objects in images and accurately quantifying the spatial and semantic uncertainties of the detections.
End-to-End Diagnosis and Segmentation Learning from Cardiac Magnetic Resonance Imaging
In this paper, we propose a learning method to train diagnosis models, where our approach is designed to work with relatively small datasets.
Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks
Furthermore, the proposed measurements also allow us to show that it is possible to optimise the training process with a new dynamic sampling training approach that continuously and automatically change the mini-batch size and learning rate during the training process.
Pre and Post-hoc Diagnosis and Interpretation of Malignancy from Breast DCE-MRI
Conversely, traditional approaches follow a pre-hoc approach that initially localises suspicious areas that are subsequently classified to establish the breast malignancy -- this approach is trained using strongly annotated data (i. e., it needs a delineation and classification of all lesions in an image).
Multi-modal Cycle-consistent Generalized Zero-Shot Learning
In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes, while testing uses the visual representations of the seen and unseen classes.
Ranked #6 on
Generalized Zero-Shot Learning
on SUN Attribute
Model Agnostic Saliency for Weakly Supervised Lesion Detection from Breast DCE-MRI
There is a heated debate on how to interpret the decisions provided by deep learning models (DLM), where the main approaches rely on the visualization of salient regions to interpret the DLM classification process.
Bayesian Semantic Instance Segmentation in Open Set World
In this paper, we present a novel open-set semantic instance segmentation approach capable of segmenting all known and unknown object classes in images, based on the output of an object detector trained on known object classes.
Producing radiologist-quality reports for interpretable artificial intelligence
Current approaches to explaining the decisions of deep learning systems for medical tasks have focused on visualising the elements that have contributed to each decision.
Training Medical Image Analysis Systems like Radiologists
This process bears no direct resemblance with radiologist training, which is based on solving a series of tasks of increasing difficulty, where each task involves the use of significantly smaller datasets than those used in machine learning.
Detecting hip fractures with radiologist-level performance using deep neural networks
We developed an automated deep learning system to detect hip fractures from frontal pelvic x-rays, an important and common radiological task.
A Bayesian Data Augmentation Approach for Learning Deep Models
Data augmentation is an essential part of the training process applied to deep learning models.
Smart Mining for Deep Metric Learning
In this paper, we propose a novel deep metric learning method that combines the triplet model and the global structure of the embedding space.
Automated Detection of Individual Micro-calcifications from Mammograms using a Multi-stage Cascade Approach
In mammography, the efficacy of computer-aided detection methods depends, in part, on the robust localisation of micro-calcifications ($\mu$C).
Automated 5-year Mortality Prediction using Deep Learning and Radiomics Features from Chest Computed Tomography
We propose new methods for the prediction of 5-year mortality in elderly individuals using chest computed tomography (CT).
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
In this work we propose a unsupervised framework to learn a deep convolutional neural network for single view depth predic- tion, without requiring a pre-training stage or annotated ground truth depths.
Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions
Current results from machine learning show that replacing this siamese by a triplet network can improve the classification accuracy in several problems, but this has yet to be demonstrated for local image descriptor learning.
Weakly-Supervised Structured Output Learning With Flexible and Latent Graphs Using High-Order Loss Functions
We introduce two new structured output models that use a latent graph, which is flexible in terms of the number of nodes and structure, where the training process minimises a high-order loss function using a weakly annotated training set.
Competitive Multi-scale Convolution
In this paper, we introduce a new deep convolutional neural network (ConvNet) module that promotes competition among a set of multi-scale convolutional filters.
Ranked #18 on
Image Classification
on MNIST
On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units
The combination of deep learning models and piecewise linear activation functions allows for the estimation of exponentially complex functions with the use of a large number of subnetworks specialized in the classification of similar input examples.
Ranked #24 on
Image Classification
on MNIST
Robust Optimization for Deep Regression
Convolutional Neural Networks (ConvNets) have successfully contributed to improve the accuracy of regression-based methods for computer vision tasks such as human pose estimation, landmark localization, and object detection.
Deep Structured learning for mass segmentation from Mammograms
In this paper, we present a novel method for the segmentation of breast masses from mammograms exploring structured and deep learning.
Non-rigid Segmentation using Sparse Low Dimensional Manifolds and Deep Belief Networks
In this paper, we propose a new methodology for segmenting non-rigid visual objects, where the search procedure is onducted directly on a sparse low-dimensional manifold, guided by the classification results computed from a deep belief network.
Fully Automated Non-rigid Segmentation with Distance Regularized Level Set Evolution Initialized and Constrained by Deep-structured Inference
We address these two issues with an innovative structured inference using deep belief networks that produces reliable initial guess and appearance model.
Top-Down Segmentation of Non-rigid Visual Objects Using Derivative-Based Search on Sparse Manifolds
In this paper, we propose the use of sparse manifolds to reduce the dimensionality of the rigid detection search space of current stateof-the-art top-down segmentation methodologies.
