PhD Student
Dina is a PhD student in the Computer Science Department at Boston University, advised by Professor Kate Saenko. Prior to that, she received her BSc and MSc in Computer Science at Kazan Federal University.
Her research is focused on computer vision, deep learning, and pixel-level domain adaptation. Specifically, she is interested in realistic unsupervised image-to-image and video-to-video translation using generative models. She is also passionate about computer-aided healthcare systems.
Publications
Dina Bashkirova, Ben Usman and Kate Saenko. (2019). “Adversarial Self-Defense for Cycle-Consistent GANs.”. http://dbash.github.io/files/self_adversarial.pdf
Dina Bashkirova, Ben Usman and Kate Saenko. (2018). “Unsupervised Video-to-Video Translation.”. http://dbash.github.io/files/uns_v2v_ICLR19.pdf
Dina Bashkirova, Shin Yoshizawa, Roustam Latypov and Hideo Yokota. (2017). “Fast L1 Gauss Transforms for Edge-Aware Image Filtering.” Proceedings of ISP RAS. http://dbash.github.io/files/fast_l1_gaussian_filter.pdf
Dina Bashkirova. (2016). “Convolutional Neural Networks for Image Steganalysis.” BioNanoScience. http://dbash.github.io/files/bashkirova cnn steganalysis.pdf