Generally, image-to-image translation (i2i) methods aim at learning mapp...
Neural network ensembles have been studied extensively in the context of...
We propose an analysis in fair learning that preserves the utility of th...
We consider a fair representation learning perspective, where optimal
pr...
In image classification, it is common practice to train deep networks to...
Most image-to-image translation methods focus on learning mappings acros...
A crucial aspect in reliable machine learning is to design a deployable
...
Multi-source domain adaptation aims at leveraging the knowledge from mul...
The no free lunch theorem states that no model is better suited to every...
Traditionally, the main focus of image super-resolution techniques is on...
We introduce Persistent Mixture Model (PMM) networks for representation
...
We reveal the incoherence between the widely-adopted empirical domain
ad...
In the object detection task, merging various datasets from similar cont...
We aim at demonstrating the influence of diversity in the ensemble of CN...
Computer vision datasets containing multiple modalities such as color, d...
Few-shot image classification aims at training a model by using only a f...
The uncertainty estimation is critical in real-world decision making
app...
In this paper, we proposed a unified and principled method for both quer...
We present a method to estimate lighting from a single image of an indoo...
Vanilla CNNs, as uncalibrated classifiers, suffer from classifying
out-o...
Great performances of deep learning are undeniable, with impressive resu...
Multitask learning aims at solving a set of related tasks simultaneously...
To evaluate their performance, existing dehazing approaches generally re...
However Deep neural networks recently have achieved impressive results f...
Lifelong learning can be viewed as a continuous transfer learning proced...
Convolutional Neural Networks (CNNs) allowed improving the state-of-the-...
Incremental learning from non-stationary data poses special challenges t...
Detection and rejection of adversarial examples in security sensitive an...
With super-resolution optical microscopy, it is now possible to observe
...
Calibrating the confidence of supervised learning models is important fo...
The easiness at which adversarial instances can be generated in deep neu...
Assisting users by suggesting completed queries as they type is a common...
We propose an automatic method to infer high dynamic range illumination ...
We are proposing to use an ensemble of diverse specialists, where specia...
Many real-world applications are characterized by a number of conflictin...
The storage and computation requirements of Convolutional Neural Network...
This paper proposes a self-adaptation mechanism to manage the resources
...