Search Results for author:
Found 40 papers, 12 papers with code
Analyzing Data Augmentation for Medical Images: A Case Study in Ultrasound Images
Data augmentation is one of the most effective techniques to improve the generalization performance of deep neural networks.
Improving genetic algorithms performance via deterministic population shrinkage
Despite the intuition that the same population size is not needed throughout the run of an Evolutionary Algorithm (EA), most EAs use a fixed population size.
Filtering Pixel Latent Variables for Unmixing Noisy and Undersampled Volumetric Images
The development of robust signal unmixing algorithms is essential for leveraging multimodal datasets acquired through a wide array of scientific imaging technologies, including hyperspectral or time-resolved acquisitions.
Hessian Aware Low-Rank Weight Perturbation for Continual Learning
We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method.
Domain Agnostic Image-to-image Translation using Low-Resolution Conditioning
Conditioned on a target image, such methods extract the target style and combine it with the source image content, keeping coherence between the domains.
Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes
Neural network ensembles have been studied extensively in the context of adversarial robustness and most ensemble-based approaches remain vulnerable to adaptive attacks.
On Learning Fairness and Accuracy on Multiple Subgroups
In the upper-level, the fair predictor is updated to be close to all subgroup specific predictors.
Evolving Domain Generalization
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data.
Fair Representation Learning through Implicit Path Alignment
We consider a fair representation learning perspective, where optimal predictors, on top of the data representation, are ensured to be invariant with respect to different sub-groups.
Matching Feature Sets for Few-Shot Image Classification
In image classification, it is common practice to train deep networks to extract a single feature vector per input image.
Gap Minimization for Knowledge Sharing and Transfer
Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e. g., $\mathcal{H}$-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees.
On the benefits of representation regularization in invariance based domain generalization
Our regularization is orthogonal to and can be straightforwardly adopted in existing domain generalization algorithms for invariant representation learning.
Aggregating From Multiple Target-Shifted Sources
Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain.
Meta Learning Black-Box Population-Based Optimizers
From that framework's formulation, we propose to parameterize the algorithm using deep recurrent neural networks and use a meta-loss function based on stochastic algorithms' performance to train efficient data-driven optimizers over several related optimization tasks.
A Generative Model for Hallucinating Diverse Versions of Super Resolution Images
Traditionally, the main focus of image super-resolution techniques is on recovering the most likely high-quality images from low-quality images, using a one-to-one low- to high-resolution mapping.
Unified Principles For Multi-Source Transfer Learning Under Label Shifts
We study the label shift problem in multi-source transfer learning and derive new generic principles to control the target generalization risk.
Mixture-based Feature Space Learning for Few-shot Image Classification
In contrast, we propose to model base classes with mixture models by simultaneously training the feature extractor and learning the mixture model parameters in an online manner.
Beyond $\mathcal{H}$-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence
We reveal the incoherence between the widely-adopted empirical domain adversarial training and its generally-assumed theoretical counterpart based on $\mathcal{H}$-divergence.
Input Dropout for Spatially Aligned Modalities
Computer vision datasets containing multiple modalities such as color, depth, and thermal properties are now commonly accessible and useful for solving a wide array of challenging tasks.
Associative Alignment for Few-shot Image Classification
Few-shot image classification aims at training a model from only a few examples for each of the "novel" classes.
Deep Active Learning: Unified and Principled Method for Query and Training
In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning.
Deep Parametric Indoor Lighting Estimation
We present a method to estimate lighting from a single image of an indoor scene.
Unsupervised Temperature Scaling: An Unsupervised Post-Processing Calibration Method of Deep Networks
The great performances of deep learning are undeniable, with impressive results over a wide range of tasks.
Controlling Over-generalization and its Effect on Adversarial Examples Detection and Generation
As an appropriate training set for the extra class, we introduce two resources that are computationally efficient to obtain: a representative natural out-distribution set and interpolated in-distribution samples.
A Principled Approach for Learning Task Similarity in Multitask Learning
Hence, an important aspect of multitask learning is to understand the similarities within a set of tasks.
Learning of Image Dehazing Models for Segmentation Tasks
To evaluate their performance, existing dehazing approaches generally rely on distance measures between the generated image and its corresponding ground truth.
Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks
Temperature Scaling (TS) is a state-of-the-art among measure-based calibration methods which has low time and memory complexity as well as effectiveness.
Accumulating Knowledge for Lifelong Online Learning
We are providing a theoretical analysis of this algorithm, with a cumulative error upper bound for each task.
Evaluating and Characterizing Incremental Learning from Non-Stationary Data
Incremental learning from non-stationary data poses special challenges to the field of machine learning.
Towards Dependable Deep Convolutional Neural Networks (CNNs) with Out-distribution Learning
Detection and rejection of adversarial examples in security sensitive and safety-critical systems using deep CNNs is essential.
Learning to Become an Expert: Deep Networks Applied To Super-Resolution Microscopy
More specifically, we are proposing a system based on a deep neural network that can provide a quantitative quality measure of a STED image of neuronal structures given as input.
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them.
Diversity regularization in deep ensembles
Calibrating the confidence of supervised learning models is important for a variety of contexts where the certainty over predictions should be reliable.
Out-distribution training confers robustness to deep neural networks
The easiness at which adversarial instances can be generated in deep neural networks raises some fundamental questions on their functioning and concerns on their use in critical systems.
Learning to Predict Indoor Illumination from a Single Image
We propose an automatic method to infer high dynamic range illumination from a single, limited field-of-view, low dynamic range photograph of an indoor scene.
Robustness to Adversarial Examples through an Ensemble of Specialists
We are proposing to use an ensemble of diverse specialists, where speciality is defined according to the confusion matrix.
Estimating Quality in Multi-Objective Bandits Optimization
The question is: how good do estimations of these objectives have to be in order for the solution maximizing the preference function to remain unchanged?
Alternating Direction Method of Multipliers for Sparse Convolutional Neural Networks
This method alternates between promoting the sparsity of the network and optimizing the recognition performance, which allows us to exploit the two-part structure of the corresponding objective functions.
Bayesian Hyperparameter Optimization for Ensemble Learning
Our method consists in building a fixed-size ensemble, optimizing the configuration of one classifier of the ensemble at each iteration of the hyperparameter optimization algorithm, taking into consideration the interaction with the other models when evaluating potential performances.
Sustainable Cooperative Coevolution with a Multi-Armed Bandit
At each iteration, the dynamic multi-armed bandit makes a decision on which species to evolve for a generation, using the history of progress made by the different species to guide the decisions.
