no code implementations • ICCV 2023 • Amirreza Shaban, Joonho Lee, Sanghun Jung, Xiangyun Meng, Byron Boots
Existing self-training methods use a model trained on labeled source data to generate pseudo labels for target data and refine the predictions via fine-tuning the network on the pseudo labels.
no code implementations • ICCV 2023 • Joonho Lee, Jae Oh Woo, Hankyu Moon, Kwonho Lee
Deploying deep visual models can lead to performance drops due to the discrepancies between source and target distributions.
1 code implementation • 16 Nov 2022 • Joonho Lee, Gyemin Lee
Unsupervised domain adaptation (UDA) aims to improve the prediction performance in the target domain under distribution shifts from the source domain.
no code implementations • 6 Oct 2022 • Álvaro Belmonte-Baeza, Joonho Lee, Giorgio Valsecchi, Marco Hutter
We use meta reinforcement learning to train a locomotion policy that can quickly adapt to different designs.
no code implementations • 31 Aug 2022 • Joonho Lee, Gyemin Lee
Most unsupervised domain adaptation (UDA) methods assume that labeled source images are available during model adaptation.
no code implementations • 23 Mar 2022 • Eric Vollenweider, Marko Bjelonic, Victor Klemm, Nikita Rudin, Joonho Lee, Marco Hutter
Imitation learning approaches such as adversarial motion priors aim to reduce this problem by encouraging a pre-defined motion style.
no code implementations • 22 Dec 2020 • Joonho Lee, Miguel A. Morales, Fionn D. Malone
We investigate the viability of the phaseless finite temperature auxiliary field quantum Monte Carlo (ph-FT-AFQMC) method for ab initio systems using the uniform electron gas as a model.
Chemical Physics Strongly Correlated Electrons
no code implementations • 6 Nov 2020 • Joonho Lee, Dominic Berry, Craig Gidney, William J. Huggins, Jarrod R. McClean, Nathan Wiebe, Ryan Babbush
We describe quantum circuits with only $\widetilde{\cal O}(N)$ Toffoli complexity that block encode the spectra of quantum chemistry Hamiltonians in a basis of $N$ arbitrary (e. g., molecular) orbitals.
Quantum Physics Chemical Physics
1 code implementation • 21 Oct 2020 • Joonho Lee, Jemin Hwangbo, Lorenz Wellhausen, Vladlen Koltun, Marco Hutter
The trained controller has taken two generations of quadrupedal ANYmal robots to a variety of natural environments that are beyond the reach of prior published work in legged locomotion.
no code implementations • 8 Oct 2019 • José Ignacio Orlando, Huazhu Fu, João Barbossa Breda, Karel van Keer, Deepti. R. Bathula, Andrés Diaz-Pinto, Ruogu Fang, Pheng-Ann Heng, Jeyoung Kim, Joonho Lee, Joonseok Lee, Xiaoxiao Li, Peng Liu, Shuai Lu, Balamurali Murugesan, Valery Naranjo, Sai Samarth R. Phaye, Sharath M. Shankaranarayana, Apoorva Sikka, Jaemin Son, Anton Van Den Hengel, Shujun Wang, Junyan Wu, Zifeng Wu, Guanghui Xu, Yongli Xu, Pengshuai Yin, Fei Li, Yanwu Xu, Xiulan Zhang, Hrvoje Bogunović
As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one.
no code implementations • 18 Sep 2019 • Vassilios Tsounis, Mitja Alge, Joonho Lee, Farbod Farshidian, Marco Hutter
This paper addresses the problem of legged locomotion in non-flat terrain.
1 code implementation • 26 May 2019 • Kumar Shridhar, Joonho Lee, Hideaki Hayashi, Purvanshi Mehta, Brian Kenji Iwana, Seokjun Kang, Seiichi Uchida, Sheraz Ahmed, Andreas Dengel
We show that ProbAct increases the classification accuracy by +2-3% compared to ReLU or other conventional activation functions on both original datasets and when datasets are reduced to 50% and 25% of the original size.
2 code implementations • 24 Jan 2019 • Jemin Hwangbo, Joonho Lee, Alexey Dosovitskiy, Dario Bellicoso, Vassilios Tsounis, Vladlen Koltun, Marco Hutter
In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes.
no code implementations • 22 Jan 2019 • Joonho Lee, Jemin Hwangbo, Marco Hutter
We experimentally validate our approach on the quadrupedal robot ANYmal, which is a dog-sized quadrupedal system with 12 degrees of freedom.