Search Results for author:
Found 29 papers, 15 papers with code
PANDAS: Prototype-based Novel Class Discovery and Detection
In this work, we look at ways to extend a detector trained for a set of base classes so it can i) spot the presence of novel classes, and ii) automatically enrich its repertoire to be able to detect those newly discovered classes together with the base ones.
Placing Objects in Context via Inpainting for Out-of-distribution Segmentation
In our experiments, we present different anomaly segmentation datasets based on POC-generated data and show that POC can improve the performance of recent state-of-the-art anomaly fine-tuning methods in several standardized benchmarks.
RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation
Class-incremental semantic image segmentation assumes multiple model updates, each enriching the model to segment new categories.
Reliability in Semantic Segmentation: Are We on the Right Track?
We analyze a broad variety of models, spanning from older ResNet-based architectures to novel transformers and assess their reliability based on four metrics: robustness, calibration, misclassification detection and out-of-distribution (OOD) detection.
Semantic Image Segmentation: Two Decades of Research
Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image.
On the Road to Online Adaptation for Semantic Image Segmentation
We propose a new problem formulation and a corresponding evaluation framework to advance research on unsupervised domain adaptation for semantic image segmentation.
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
Recently, Wong et al. showed that adversarial training with single-step FGSM leads to a characteristic failure mode named Catastrophic Overfitting (CO), in which a model becomes suddenly vulnerable to multi-step attacks.
Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey
Semantic segmentation plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image.
Towards fast and effective single-step adversarial training
In this work, we methodically revisit the role of noise and clipping in single-step adversarial training.
Automatic Feature Extraction for Heartbeat Anomaly Detection
We focus on automatic feature extraction for raw audio heartbeat sounds, aimed at anomaly detection applications in healthcare.
Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning
In this context, we show that one way to learn models that are inherently more robust against forgetting is domain randomization - for vision tasks, randomizing the current domain's distribution with heavy image manipulations.
Accelerating MCMC algorithms through Bayesian Deep Networks
Markov Chain Monte Carlo (MCMC) algorithms are commonly used for their versatility in sampling from complicated probability distributions.
Natural Reweighted Wake-Sleep
These models are commonly trained using a two-step optimization algorithm called Wake-Sleep (WS) and more recently by improved versions, such as Reweighted Wake-Sleep (RWS) and Bidirectional Helmholtz Machines (BiHM).
Reliable Uncertainties for Bayesian Neural Networks using Alpha-divergences
Bayesian Neural Networks (BNNs) often result uncalibrated after training, usually tending towards overconfidence.
Evaluating Natural Alpha Embeddings on Intrinsic and Extrinsic Tasks
Skip-Gram is a simple, but effective, model to learn a word embedding mapping by estimating a conditional probability distribution for each word of the dictionary.
Constraining the Reionization History using Bayesian Normalizing Flows
Additionally, we demonstrate the advantages of Normalizing Flows (NF) combined with BNNs, being able to model more complex output distributions and thus capture key information as non-Gaussianities in the parameter conditional density distribution for astrophysical and cosmological dataset.
Parameters Estimation from the 21 cm signal using Variational Inference
Upcoming experiments such as Hydrogen Epoch of Reionization Array (HERA) and Square Kilometre Array (SKA) are intended to measure the 21cm signal over a wide range of redshifts, representing an incredible opportunity in advancing our understanding about the nature of cosmic Reionization.
Learning Unbiased Representations via Mutual Information Backpropagation
We are interested in learning data-driven representations that can generalize well, even when trained on inherently biased data.
Explainable Deep Classification Models for Domain Generalization
Explanations are defined as regions of visual evidence upon which a deep classification network makes a decision.
Generative Pseudo-label Refinement for Unsupervised Domain Adaptation
We exploit this finding in an iterative procedure where a generative model and a classifier are jointly trained: in turn, the generator allows to sample cleaner data from the target distribution, and the classifier allows to associate better labels to target samples, progressively refining target pseudo-labels.
Natural Alpha Embeddings
Learning an embedding for a large collection of items is a popular approach to overcome the computational limitations associated to one-hot encodings.
Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
In the second part of the paper, we present a guide to the training and calibration of a successful multi-channel BNN for the CMB temperature and polarization map.
Addressing Model Vulnerability to Distributional Shifts over Image Transformation Sets
We are concerned with the vulnerability of computer vision models to distributional shifts.
Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds
In this paper we propose two novel bounds for the log-likelihood based on Kullback-Leibler and the R\'{e}nyi divergences, which can be used for variational inference and in particular for the training of Variational AutoEncoders.
Generalizing to Unseen Domains via Adversarial Data Augmentation
Only using training data from a single source distribution, we propose an iterative procedure that augments the dataset with examples from a fictitious target domain that is "hard" under the current model.
Adversarial Feature Augmentation for Unsupervised Domain Adaptation
Recent works showed that Generative Adversarial Networks (GANs) can be successfully applied in unsupervised domain adaptation, where, given a labeled source dataset and an unlabeled target dataset, the goal is to train powerful classifiers for the target samples.
Certifying Some Distributional Robustness with Principled Adversarial Training
Neural networks are vulnerable to adversarial examples and researchers have proposed many heuristic attack and defense mechanisms.
Curriculum Dropout
This induces an adaptive regularization scheme that smoothly increases the difficulty of the optimization problem.
Modeling Retinal Ganglion Cell Population Activity with Restricted Boltzmann Machines
The idea was to figure out if binary latent states encode the regularities associated to different visual stimuli, as modes in the joint distribution.
