This event has passed.

TRAIL-VAIA Doctoral School – Interpretation and Explanation of Deep Computer Vision

Name: TRAIL-VAIA Doctoral School – Interpretation and Explanation of Deep Computer Vision
Start: 2023-01-17T14:00:00+01:00
End: 2023-01-17T16:30:00+01:00
Location: Online

17 janvier 2023 at 14 h 00 min - 16 h 30 min

In brief

In 2012, AlexNet [Krizhevsky et al., NeurIPS’12] shook the field with the remarkable performance it obtained on the task of image recognition at a large scale. This showed the potential of artificial neural networks, and deep models in general, for modeling visual data. At the same time, this motivated the adoption of deep models by both academia and industry to the point of making these models the standard when building AI systems for visual data.

Despite their high predictive performance, follow up work showed that the complex structure that characterize these models obscures what characteristics or features of the training data are internally encoded in the model (Interpretation). At the same time, it is hard to assess what characteristics from a given input are considered by the model when making a prediction for such input.

In this course we will discuss relevant methods that have been proposed to address these two tasks, introduce some evaluation protocols and set some perspectives towards current and future directions.