1 citations · 1 across the 1 of their papers we have counts for
6 papers
How Transferable are Reasoning Patterns in VQA?
Corentin Kervadec, Theo Jaunet, Grigory Antipov +3
Since its inception, Visual Question Answering (VQA) is notoriously known as a task, where models are prone to exploit biases in datasets to find shortcuts instead of performing hi…
Estimating semantic structure for the VQA answer space
Corentin Kervadec, Grigory Antipov, Moez Baccouche +1
Since its appearance, Visual Question Answering (VQA, i.e. answering a question posed over an image), has always been treated as a classification problem over a set of predefined a…
Roses Are Red, Violets Are Blue... but Should Vqa Expect Them To?
Corentin Kervadec, Grigory Antipov, Moez Baccouche +1
Models for Visual Question Answering (VQA) are notorious for their tendency to rely on dataset biases, as the large and unbalanced diversity of questions and concepts involved and…
Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks
Corentin Kervadec, Grigory Antipov, Moez Baccouche +1
The large adoption of the self-attention (i.e. transformer model) and BERT-like training principles has recently resulted in a number of high performing models on a large panoply o…
MFAS: Multimodal Fusion Architecture Search
Juan-Manuel Pérez-Rúa, Valentin Vielzeuf, Stéphane Pateux +2
We tackle the problem of finding good architectures for multimodal classification problems. We propose a novel and generic search space that spans a large number of possible fusion…
Efficient Progressive Neural Architecture Search
Juan-Manuel Perez-Rua, Moez Baccouche, Stephane Pateux
This paper addresses the difficult problem of finding an optimal neural architecture design for a given image classification task. We propose a method that aggregates two main resu…