Search Results for author:
Found 9 papers, 8 papers with code
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
In this work, we examine this approach and identify potential hazards associated with the use of log-likelihood in conjunction with gradient-based optimizers.
Bridging the Gap to Real-World Object-Centric Learning
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world.
Causal Influence Detection for Improving Efficiency in Reinforcement Learning
Many reinforcement learning (RL) environments consist of independent entities that interact sparsely.
Adversarial and Perceptual Refinement for Compressed Sensing MRI Reconstruction
In addition, we introduce a semantic interpretability score, measuring the visibility of the region of interest in both ground truth and reconstructed images, which allows us to objectively quantify the usefulness of the image quality for image post-processing and analysis.
Self-supervised Visual Reinforcement Learning with Object-centric Representations
We show that the structure in the representations in combination with goal-conditioned attention policies helps the autonomous agent to discover and learn useful skills.
Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities
Recently, it was shown that the reconstruction of pre-trained self-supervised features leads to object-centric representations on unconstrained real-world image datasets.
NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Aggregated Convolutional Feature Maps
This report to our stage 1 submission to the NeurIPS 2019 disentanglement challenge presents a simple image preprocessing method for training VAEs leading to improved disentanglement compared to directly using the images.
NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Learned Aggregation of Convolutional Feature Maps
This report to our stage 2 submission to the NeurIPS 2019 disentanglement challenge presents a simple image preprocessing method for learning disentangled latent factors.
DyST: Towards Dynamic Neural Scene Representations on Real-World Videos
Our Dynamic Scene Transformer (DyST) model leverages recent work in neural scene representation to learn a latent decomposition of monocular real-world videos into scene content, per-view scene dynamics, and camera pose.
