LDCE harnesses the capabilities of recent class- or text-conditional foundation latent diffusion models to expedite counterfactual generation and focus on the important, semantic parts of the data.
We show the efficacy of our approach across a wide spectrum of study areas and time scales.
In this paper, we show that nearest-neighbor approaches also yield state-of-the-art results on dense novelty detection in complex driving scenes when working with an appropriate feature representation.
Ranked #1 on Anomaly Detection on Fishyscapes L&F (using extra training data)
This work presents improvements in monocular hand shape estimation by building on top of recent advances in unsupervised learning.
Visual domain randomization in simulated environments is a widely used method to transfer policies trained in simulation to real robots.
One-shot imitation is the vision of robot programming from a single demonstration, rather than by tedious construction of computer code.
In this paper, we present a network architecture for video generation that models spatio-temporal consistency without resorting to costly 3D architectures.
We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for reinforcement learning in the presence of sparse rewards.
Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of morbidity and mortality.
Off-policy temporal difference (TD) methods are a powerful class of reinforcement learning (RL) algorithms.
We show that methods trained on our dataset consistently perform well when tested on other datasets.
Ranked #8 on 3D Hand Pose Estimation on FreiHAND
Sample efficiency is a crucial problem in deep reinforcement learning.
Reinforcement learning optimizes policies for expected cumulative reward.