research
∙
09/23/2022
TeST: Test-time Self-Training under Distribution Shift
Despite their recent success, deep neural networks continue to perform p...
share
research
∙
10/13/2021
Unsupervised Object Learning via Common Fate
Learning generative object models from unlabelled videos is a long stand...
research
∙
10/12/2021
Dynamic Inference with Neural Interpreters
Modern neural network architectures can leverage large amounts of data t...
research
∙
10/11/2021
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
Predicting the future trajectory of a moving agent can be easy when the ...
research
∙
09/30/2021
CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
Contrastive learning allows us to flexibly define powerful losses by con...
research
∙
07/17/2021
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
An important component for generalization in machine learning is to unco...
research
∙
07/12/2021
Representation Learning for Out-Of-Distribution Generalization in Reinforcement Learning
Learning data representations that are useful for various downstream tas...
research
∙
07/02/2021
Backward-Compatible Prediction Updates: A Probabilistic Approach
When machine learning systems meet real world applications, accuracy is ...
research
∙
06/15/2021
Towards Total Recall in Industrial Anomaly Detection
Being able to spot defective parts is a critical component in large-scal...
research
∙
04/27/2021
Adapting ImageNet-scale models to complex distribution shifts with self-learning
While self-learning methods are an important component in many recent do...
research
∙
04/27/2020
Towards causal generative scene models via competition of experts
Learning how to model complex scenes in a modular way with recombinable ...
research
∙
05/30/2018
Rehabilitating the Color Checker Dataset for Illuminant Estimation
In a previous work, it was shown that there is a curious problem with th...
research
∙
05/09/2018
Deep Directional Statistics: Pose Estimation with Uncertainty Quantification
Modern deep learning systems successfully solve many perception tasks su...
research
∙
07/27/2016
Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
We describe the first method to automatically estimate the 3D pose of th...
research
∙
03/17/2015
3D Object Class Detection in the Wild
Object class detection has been a synonym for 2D bounding box localizati...
research
∙
12/20/2013