no code implementations • 5 Jan 2024 • SeokHyun Seo, Jinwoo Hong, JungWoo Chae, Kyungyul Kim, Sangheum Hwang
Through experimental analysis using attention maps in ViT, we observe that the rich representations deteriorate when trained on a small dataset.
no code implementations • 7 Apr 2023 • Jae-Hun Lee, Doyoung Yoon, ByeongMoon Ji, Kyungyul Kim, Sangheum Hwang
Linear probing (LP) (and $k$-NN) on the upstream dataset with labels (e. g., ImageNet) and transfer learning (TL) to various downstream datasets are commonly employed to evaluate the quality of visual representations learned via self-supervised learning (SSL).
1 code implementation • ICCV 2021 • Kyungyul Kim, ByeongMoon Ji, Doyoung Yoon, Sangheum Hwang
Hence, it can be interpreted within a framework of knowledge distillation as a student becomes a teacher itself.
Ranked #1 on Multimodal Machine Translation on Multi30K (BLUE (DE-EN) metric)
no code implementations • 19 Sep 2019 • Jihyeun Yoon, Kyungyul Kim, Jongseong Jang
Deep Neural Network based classifiers are known to be vulnerable to perturbations of inputs constructed by an adversarial attack to force misclassification.
Adversarial Attack Explainable Artificial Intelligence (XAI)
no code implementations • 30 Aug 2019 • Byeongmoon Ji, Hyemin Jung, Jihyeun Yoon, Kyungyul Kim, Younghak Shin
The prediction reliability of neural networks is important in many applications.