Search Results for author:
Found 17 papers, 5 papers with code
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Representation Learning
This revealed that the driving factor behind both, the modality gap and the object bias, is the information imbalance between images and captions.
DITTO: Demonstration Imitation by Trajectory Transformation
Subsequently, in the live online trajectory generation stage, we first \mbox{re-detect} all objects, then we warp the demonstration trajectory to the current scene, and finally, we trace the trajectory with the robot.
Latent Diffusion Counterfactual Explanations
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.
Climate-sensitive Urban Planning through Optimization of Tree Placements
We show the efficacy of our approach across a wide spectrum of study areas and time scales.
Compositional Servoing by Recombining Demonstrations
In this work, we present a framework that formulates the visual servoing task as graph traversal.
Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection
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)
Conditional Visual Servoing for Multi-Step Tasks
Visual Servoing has been effectively used to move a robot into specific target locations or to track a recorded demonstration.
Contrastive Representation Learning for Hand Shape Estimation
This work presents improvements in monocular hand shape estimation by building on top of recent advances in unsupervised learning.
Pre-training of Deep RL Agents for Improved Learning under Domain Randomization
Visual domain randomization in simulated environments is a widely used method to transfer policies trained in simulation to real robots.
FlowControl: Optical Flow Based Visual Servoing
One-shot imitation is the vision of robot programming from a single demonstration, rather than by tedious construction of computer code.
Temporal Shift GAN for Large Scale Video Generation
In this paper, we present a network architecture for video generation that models spatio-temporal consistency without resorting to costly 3D architectures.
Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control
We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for reinforcement learning in the presence of sparse rewards.
Function Follows Form: Regression from Complete Thoracic Computed Tomography Scans
Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of morbidity and mortality.
CrossNorm: On Normalization for Off-Policy Reinforcement Learning
Off-policy temporal difference (TD) methods are a powerful class of reinforcement learning (RL) algorithms.
FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images
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
CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
Sample efficiency is a crucial problem in deep reinforcement learning.
Loss is its own Reward: Self-Supervision for Reinforcement Learning
Reinforcement learning optimizes policies for expected cumulative reward.
