객원교원 1 페이지 | 서울대학교AI연구원(AIIS)

사람들

객원교원

7

김진화 객원교원

  • 전공 (연구분야)Multimodal Deep Learning
  • 연구분야(AI 원천기술)
  • 연구분야(X+AI)

대표논문

Kim, J.-H., Kim, Y., Lee, J., Yoo, K. M., & Lee, S.-W. (2022). Mutual Information Divergence: A Unified Metric for Multimodal Generative Models. ArXiv Preprint ArXiv:2205.13445.
Kim, J.-H., Jun, J., & Zhang, B.-T. (2018). Bilinear Attention Networks. Advances in Neural Information Processing Systems 31 (NeurIPS).
Kim, J.-H., On, K. W., Lim, W., Kim, J., Ha, J.-W., & Zhang, B.-T. (2017, October). Hadamard Product for Low-rank Bilinear Pooling. The 5th International Conference on Learning Representations (ICLR).
6

송은우 객원교원

  • 전공 (연구분야)Speech Signal Processing, Speech Synthesis
  • 연구분야(AI 원천기술)
  • 연구분야(X+AI)

대표논문

R. Yamamoto, E. Song, J.-M. Kim, “Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram, Proc. ICASSP, 2020, pp. 6194-6198.

E. Song, F. K. Soong, H.-G. Kang, “Effective spectral and excitation modeling techniques for LSTM-RNN-based speech synthesis systems,” IEEE/ACM Trans. Audio, Speech, and Lang. Process., vol. 25, no. 11, pp. 2152–2161, 2017."
5

유강민 객원교원

  • 전공 (연구분야)컴퓨터공학 전공 (분야: 자연어처리, 머신러닝)
  • 연구분야(AI 원천기술)
  • 연구분야(X+AI)

대표논문

Data augmentation for spoken language understanding via joint variational generation
4
  • 전공 (연구분야)Computer Vision, Machine Learning
  • 연구분야(AI 원천기술)
  • 연구분야(X+AI)

대표논문

Variational autoencoded regression: high dimensional regression of visual data on complex manifold
3

윤상두 객원교원

  • 전공 (연구분야)Vision, Vision-Language
  • 연구분야(AI 원천기술)
  • 연구분야(X+AI)

대표논문

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features, ICCV'21
2

허병호 객원교원

  • 전공 (연구분야)Image Classification, Backbone
  • 연구분야(AI 원천기술)
  • 연구분야(X+AI)

대표논문

Rethinking Spatial Dimensions of Vision Transformers Byeongho Heo, Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, Junsuk Choe, Seong Joon Oh IEEE International Conference on Computer Vision (ICCV), 2021

AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights Byeongho Heo*, Sanghyuk Chun*, Seong Joon Oh, Dongyoon Han, Sangdoo Yun,  Gyuwan Kim, Youngjung Uh, Jung-Woo Ha International Conference on Learning Representations (ICLR), 2021

A Comprehensive Overhaul of Feature Distillation Byeongho Heo, Jeesoo Kim, Sangdoo Yun, Hyojin Park, Nojun Kwak, and Jin Young Choi IEEE International Conference on Computer Vision (ICCV), 2019
1

윤홍일 객원교원

  • 전공 (연구분야)Computer Architecture (ML accelerators & SoC architecture, Hardware-software co-designs, and memory subsystem)
  • 연구분야(AI 원천기술)
  • 연구분야(X+AI)

대표논문

검색