seminars

Patrick Perez and Matthieu Cord presents Two talks of Patrick Perez and Matthieu Cord

On 2019-04-18 10:00 at E112, Karlovo náměstí 13, Praha 2
Speaker: Patrick Pérez
Title: ADVENT: Adversarial Entropy Minimization for Domain Adaptation in
Semantic Segmentation (CVPR 2019)
Abstract: Semantic segmentation is a key problem for many computer vision
tasks.
While approaches based on convolutional neural networks constantly break new
records on different benchmarks, generalizing well to diverse testing
environments remains a major challenge. In numerous real world applications,
there is indeed a large gap between data distributions in train and test
domains, which results in severe performance loss at run-time. In this work, we
address the task of unsupervised domain adaptation in semantic segmentation
with
losses based on the entropy of the pixel-wise predictions. To this end, we
propose two novel, complementary methods using (i) entropy loss and (ii)
adversarial loss respectively. We demonstrate state-of-the-art performance in
semantic segmentation on two challenging “synthetic-2-real” set-ups and
show
that the approach can also be used for detection.

Patrick Pérez is Scientific Director of valeo.ai, a Valeo AI research lab
focused on self-driving cars.
https://ptrckprz.github.io

Speaker: Matthieu Cord
Title: Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary
Block
for Visual Detection (NIPS 2018)
Abstract: Multi-Task Learning (MTL) is appealing for deep learning
regularization. In this paper, we tackle a specific MTL context denoted as
primary MTL, where the ultimate goal is to improve the performance of a given
primary task by leveraging several other auxiliary tasks. Our main
methodological contribution is to introduce ROCK, a new generic multi-modal
fusion block for deep learning tailored to the primary MTL context. ROCK
architecture is based on a residual connection, which makes forward prediction
explicitly impacted by the intermediate auxiliary representations. The
auxiliary
predictor's architecture is also specifically designed to our primary MTL
context, by incorporating intensive pooling operators for maximizing
complementarity of intermediate representations. Extensive experiments on NYUv2
dataset (object detection with scene classification, depth prediction, and
surface normal estimation as auxiliary tasks) validate the relevance of the
approach and its superiority to flat MTL approaches. Our method outperforms
state-of-the-art object detection models on NYUv2 dataset by a large margin,
and
is also able to handle large-scale heterogeneous inputs (real and synthetic
images) with missing annotation modalities.

Matthieu Cord, is a professor at Sorbonne University,
http://webia.lip6.fr/~cord/
Responsible person: Petr Pošík