Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Berthelot, David"'
Autor:
Berthelot, David, Autef, Arnaud, Lin, Jierui, Yap, Dian Ang, Zhai, Shuangfei, Hu, Siyuan, Zheng, Daniel, Talbott, Walter, Gu, Eric
Denoising Diffusion models have demonstrated their proficiency for generative sampling. However, generating good samples often requires many iterations. Consequently, techniques such as binary time-distillation (BTD) have been proposed to reduce the
Externí odkaz:
http://arxiv.org/abs/2303.04248
We extend semi-supervised learning to the problem of domain adaptation to learn significantly higher-accuracy models that train on one data distribution and test on a different one. With the goal of generality, we introduce AdaMatch, a method that un
Externí odkaz:
http://arxiv.org/abs/2106.04732
Autor:
Lee, Jihyeon, Xu, Joseph Z., Sohn, Kihyuk, Lu, Wenhan, Berthelot, David, Gur, Izzeddin, Khaitan, Pranav, Ke-Wei, Huang, Koupparis, Kyriacos, Kowatsch, Bernhard
To respond to disasters such as earthquakes, wildfires, and armed conflicts, humanitarian organizations require accurate and timely data in the form of damage assessments, which indicate what buildings and population centers have been most affected.
Externí odkaz:
http://arxiv.org/abs/2011.14004
Generating realistic images is difficult, and many formulations for this task have been proposed recently. If we restrict the task to that of generating a particular class of images, however, the task becomes more tractable. That is to say, instead o
Externí odkaz:
http://arxiv.org/abs/2003.02365
One promising approach to dealing with datapoints that are outside of the initial training distribution (OOD) is to create new classes that capture similarities in the datapoints previously rejected as uncategorizable. Systems that generate labels ca
Externí odkaz:
http://arxiv.org/abs/2002.03480
Autor:
Sohn, Kihyuk, Berthelot, David, Li, Chun-Liang, Zhang, Zizhao, Carlini, Nicholas, Cubuk, Ekin D., Kurakin, Alex, Zhang, Han, Raffel, Colin
Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization and pseudo
Externí odkaz:
http://arxiv.org/abs/2001.07685
We propose using active learning based techniques to further improve the state-of-the-art semi-supervised learning MixMatch algorithm. We provide a thorough empirical evaluation of several active-learning and baseline methods, which successfully demo
Externí odkaz:
http://arxiv.org/abs/1912.00594
Autor:
Berthelot, David, Carlini, Nicholas, Cubuk, Ekin D., Kurakin, Alex, Sohn, Kihyuk, Zhang, Han, Raffel, Colin
We improve the recently-proposed "MixMatch" semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribution of predictions on unlabel
Externí odkaz:
http://arxiv.org/abs/1911.09785
In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: *accuracy*, i.e., performing well on the underlying
Externí odkaz:
http://arxiv.org/abs/1909.01838