Search Results for author:
Found 40 papers, 30 papers with code
GIFT: A Framework for Global Interpretable Faithful Textual Explanations of Vision Classifiers
Understanding deep models is crucial for deploying them in safety-critical applications.
The BRAVO Semantic Segmentation Challenge Results in UNCV2024
We propose the unified BRAVO challenge to benchmark the reliability of semantic segmentation models under realistic perturbations and unknown out-of-distribution (OOD) scenarios.
PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation
We introduce a novel approach for 3D whole-body pose estimation, addressing the challenge of scale -- and deformability -- variance across body parts brought by the challenge of extending the 17 major joints on the human body to fine-grained keypoints on the face and hands.
Valeo4Cast: A Modular Approach to End-to-End Forecasting
In end-to-end forecasting, the model must jointly detect and track from sensor data (cameras or LiDARs) the past trajectories of the different elements of the scene and predict their future locations.
Back to the Basics on Predicting Transfer Performance
In the evolving landscape of deep learning, selecting the best pre-trained models from a growing number of choices is a challenge.
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
By constraining the outputs to lie on the human pose manifold, ManiPose guarantees the consistency of all hypothetical poses, in contrast to previous works.
DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
We present an innovative approach to 3D Human Pose Estimation (3D-HPE) by integrating cutting-edge diffusion models, which have revolutionized diverse fields, but are relatively unexplored in 3D-HPE.
The Performance of Transferability Metrics does not Translate to Medical Tasks
Transfer learning boosts the performance of medical image analysis by enabling deep learning (DL) on small datasets through the knowledge acquired from large ones.
Test-Time Selection for Robust Skin Lesion Analysis
Skin lesion analysis models are biased by artifacts placed during image acquisition, which influence model predictions despite carrying no clinical information.
Slimmable Encoders for Flexible Split DNNs in Bandwidth and Resource Constrained IoT Systems
In approaches based on edge computing the execution of the models is offloaded to a compute-capable device positioned at the edge of 5G infrastructures.
Even Small Correlation and Diversity Shifts Pose Dataset-Bias Issues
Our protocol reveals three findings: 1) Models learn and propagate correlation shifts even with low-bias training; this poses a risk of accumulating and combining unaccountable weak biases; 2) Models learn robust features in high- and low-bias scenarios but use spurious ones if test samples have them; this suggests that spurious correlations do not impair the learning of robust features; 3) Diversity shift can reduce the reliance on spurious correlations; this is counter intuitive since we expect biased models to depend more on biases when invariant features are missing.
Artifact-Based Domain Generalization of Skin Lesion Models
We propose a pipeline that relies on artifacts annotation to enable generalization evaluation and debiasing for the challenging skin lesion analysis context.
A Survey on Deep Learning for Skin Lesion Segmentation
We analyze these works along several dimensions, including input data (datasets, preprocessing, and synthetic data generation), model design (architecture, modules, and losses), and evaluation aspects (data annotation requirements and segmentation performance).
An Evaluation of Self-Supervised Pre-Training for Skin-Lesion Analysis
Self-supervised pre-training appears as an advantageous alternative to supervised pre-trained for transfer learning.
Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation
In the past few years, mobile deep-learning deployment progressed by leaps and bounds, but solutions still struggle to accommodate its severe and fluctuating operational restrictions, which include bandwidth, latency, computation, and energy.
GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review
Despite the growing availability of high-quality public datasets, the lack of training samples is still one of the main challenges of deep-learning for skin lesion analysis.
Insights from the Future for Continual Learning
Continual learning aims to learn tasks sequentially, with (often severe) constraints on the storage of old learning samples, without suffering from catastrophic forgetting.
PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning
Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learning.
Less is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentation
Segmenting skin lesions images is relevant both for itself and for assisting in lesion classification, but suffers from the challenge in obtaining annotated data.
Debiasing Skin Lesion Datasets and Models? Not So Fast
Data-driven models are now deployed in a plethora of real-world applications - including automated diagnosis - but models learned from data risk learning biases from that same data.
Compressing Representations for Embedded Deep Learning
Despite recent advances in architectures for mobile devices, deep learning computational requirements remains prohibitive for most embedded devices.
The Six Fronts of the Generative Adversarial Networks
Generative Adversarial Networks fostered a newfound interest in generative models, resulting in a swelling wave of new works that new-coming researchers may find formidable to surf.
Handling Inter-Annotator Agreement for Automated Skin Lesion Segmentation
We also evaluate how conditioning the ground truths using different (but very simple) algorithms may help to enhance agreement and may be appropriate for some use cases.
Solo or Ensemble? Choosing a CNN Architecture for Melanoma Classification
We evaluate that claim for melanoma classification, over 9 CNNs architectures, in 5 sets of splits created on the ISIC Challenge 2017 dataset, and 3 repeated measures, resulting in 135 models.
(De)Constructing Bias on Skin Lesion Datasets
We fed models with additional clinically meaningful information, which failed to improve the results even slightly, suggesting the destruction of cogent correlations.
Skin Lesion Synthesis with Generative Adversarial Networks
Skin cancer is by far the most common type of cancer.
Data Augmentation for Skin Lesion Analysis
In this work, we investigate the impact of 13 data augmentation scenarios for melanoma classification trained on three CNNs (Inception-v4, ResNet, and DenseNet).
Deep-Learning Ensembles for Skin-Lesion Segmentation, Analysis, Classification: RECOD Titans at ISIC Challenge 2018
This extended abstract describes the participation of RECOD Titans in parts 1 to 3 of the ISIC Challenge 2018 "Skin Lesion Analysis Towards Melanoma Detection" (MICCAI 2018).
Adversarial Attacks on Variational Autoencoders
Adversarial attacks are malicious inputs that derail machine-learning models.
Data, Depth, and Design: Learning Reliable Models for Skin Lesion Analysis
We use the exhaustive trials to simulate sequential decisions and ensembles, with and without the use of privileged information from the test set.
Knowledge Transfer for Melanoma Screening with Deep Learning
Knowledge transfer impacts the performance of deep learning -- the state of the art for image classification tasks, including automated melanoma screening.
RECOD Titans at ISIC Challenge 2017
This extended abstract describes the participation of RECOD Titans in parts 1 and 3 of the ISIC Challenge 2017 "Skin Lesion Analysis Towards Melanoma Detection" (ISBI 2017).
Known Unknowns: Uncertainty Quality in Bayesian Neural Networks
We compare the following candidate neural network models: Maximum Likelihood, Bayesian Dropout, OSBA, and --- for MNIST --- the standard variational approximation.
Adversarial Images for Variational Autoencoders
We find that autoencoders are much more robust to the attack than classifiers: while some examples have tolerably small input distortion, and reasonable similarity to the target image, there is a quasi-linear trade-off between those aims.
Towards Automated Melanoma Screening: Exploring Transfer Learning Schemes
Deep learning is the current bet for image classification.
Deep Neural Networks Under Stress
In recent years, deep architectures have been used for transfer learning with state-of-the-art performance in many datasets.
Towards Automated Melanoma Screening: Proper Computer Vision & Reliable Results
In this paper we survey, analyze and criticize current art on automated melanoma screening, reimplementing a baseline technique, and proposing two novel ones.
Semantic Diversity versus Visual Diversity in Visual Dictionaries
Results for image classification show that as visual dictionaries are based on low-level visual appearances, visual diversity is more important than semantic diversity.
Exploring the Space of Adversarial Images
Adversarial examples have raised questions regarding the robustness and security of deep neural networks.
Where Is My Puppy? Retrieving Lost Dogs by Facial Features
Human facial recognizers perform poorly for dogs (up to 60. 5% accuracy), showing that dog facial recognition is not a trivial extension of human facial recognition.
