no code implementations • 4 May 2023 • Victoria Clerico, Jorge Gonzalez-Lopez, Gady Agam, Jesus Grajal
Therefore, we propose DeepRadar2022, a radar dataset used in our systematic evaluations that is available publicly and will facilitate a standard comparison between methods.
no code implementations • 20 Oct 2021 • Ying Chen, Xu Ouyang, Kaiyue Zhu, Gady Agam
We demonstrate that the proposed approach outperforms state-of-the-art methods on two common synthetic-to-real semantic segmentation benchmarks.
no code implementations • 25 Jan 2021 • Ying Chen, Xu Ouyang, Kaiyue Zhu, Gady Agam
Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is both costly and labor intensive.
no code implementations • 3 Dec 2020 • Ying Chen, Xu Ouyang, Kaiyue Zhu, Gady Agam
In this paper, we propose a novel unsupervised domain adaptation framework to address domain shift in the context of aerial semantic image segmentation.
no code implementations • 28 Aug 2020 • Xu Ouyang, Gady Agam
Optimizing the discriminator in Generative Adversarial Networks (GANs) to completion in the inner training loop is computationally prohibitive, and on finite datasets would result in overfitting.
no code implementations • 8 Jun 2018 • Xu Ouyang, Xi Zhang, Di Ma, Gady Agam
Generating images from word descriptions is a challenging task.
no code implementations • 9 May 2018 • Xi Zhang, Di Ma, Xu Ouyang, Shanshan Jiang, Lin Gan, Gady Agam
We show that by using masks the motion estimate results in a quadratic function of input features in the output layer.
no code implementations • 2 Dec 2017 • Di Ma, Xi Zhang, Xu Ouyang, Gady Agam
This paper presents a novel approach for lecture video indexing using a boosted deep convolutional neural network system.
1 code implementation • 21 Jul 2016 • Xi Zhang, Di Ma, Lin Gan, Shanshan Jiang, Gady Agam
In this paper we propose a novel extension to the SMOTE algorithm with a theoretical guarantee for improved classification performance.
no code implementations • 17 Sep 2015 • Xi Zhang, Yanwei Fu, Shanshan Jiang, Leonid Sigal, Gady Agam
In this paper, we investigate and formalize a general framework-Stacked Multichannel Autoencoder (SMCAE) that enables bridging the synthetic gap and learning from synthetic data more efficiently.
no code implementations • 11 Mar 2015 • Xi Zhang, Yanwei Fu, Andi Zang, Leonid Sigal, Gady Agam
Experimental results on two datasets validate the efficiency of our MCAE model and our methodology of generating synthetic data.