no code implementations • 4 Apr 2024 • Sabyasachi Sahoo, Mostafa ElAraby, Jonas Ngnawe, Yann Pequignot, Frederic Precioso, Christian Gagne
In this paper, we propose Layerwise EArly STopping (LEAST) for TTA to address this problem.
no code implementations • 12 Feb 2024 • Qiuhao Zeng, Wei Wang, Fan Zhou, Gezheng Xu, Ruizhi Pu, Changjian Shui, Christian Gagne, Shichun Yang, Boyu Wang, Charles X. Ling
By employing Koopman Operators, we effectively address the time-evolving distributions encountered in TDG using the principles of Koopman theory, where measurement functions are sought to establish linear transition relations between evolving domains.
1 code implementation • 23 Jul 2021 • Mohamed Abderrahmen Abid, Ihsen Hedhli, Jean-François Lalonde, Christian Gagne
This differs from previous methods that focus on translating a given image style into a target content, our translation approach being able to simultaneously imitate the style and merge the structural information of the LR target.
Ranked #5 on Image-to-Image Translation on CelebA-HQ
no code implementations • 23 May 2020 • Mahdieh Abbasi, Denis Laurendeau, Christian Gagne
With the goal of training \emph{one integrated robust object detector with high generalization performance}, we propose a training framework to overcome missing-label challenge of the merged datasets.
no code implementations • 17 May 2020 • Mahdieh Abbasi, Arezoo Rajabi, Christian Gagne, Rakesh B. Bobba
Using MNIST and CIFAR-10, we empirically verify the ability of our ensemble to detect a large portion of well-known black-box adversarial examples, which leads to a significant reduction in the risk rate of adversaries, at the expense of a small increase in the risk rate of clean samples.
no code implementations • 25 Nov 2019 • Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Christian Gagne
The uncertainty estimation is critical in real-world decision making applications, especially when distributional shift between the training and test data are prevalent.
1 code implementation • 18 Oct 2019 • Mahdieh Abbasi, Changjian Shui, Arezoo Rajabi, Christian Gagne, Rakesh Bobba
We empirically verify that the most protective OOD sets -- selected according to our metrics -- lead to A-CNNs with significantly lower generalization errors than the A-CNNs trained on the least protective ones.
no code implementations • 25 Sep 2019 • Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Christian Gagne
The uncertainty estimation is critical in real-world decision making applications, especially when distributional shift between the training and test data are prevalent.
no code implementations • 21 Aug 2018 • Mahdieh Abbasi, Arezoo Rajabi, Azadeh Sadat Mozafari, Rakesh B. Bobba, Christian Gagne
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.