Home /
Research
Showing 379 - 384 / 897
Emergent Road Rules In Multi-Agent Driving Environments
AvikPal, JonahPhilion, Yuan-HongLiao....
Published date-11/21/2020
AutonomousVehicles
For autonomous vehicles to safely share the road with human drivers, autonomous vehicles must abide by specific "road rules" that human drivers have agreed to follow. "Road rules" include rules …
SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations
Hao-ZheFeng, KezhiKong, MinghaoChen....
Published date-11/21/2020
Semi-SupervisedImageClassification, VariationalInference
Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference results. In this paper, we investigate …
Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's Decision
KwanseokOh, JeeSeokYoon, Heung-IlSuk....
Published date-11/20/2020
There exists an apparent negative correlation between performance and interpretability of deep learning models. In an effort to reduce this negative correlation, we propose Born Identity Network (BIN), which is …
Concentration inequality for U-statistics of order two for uniformly ergodic Markov chains, and applications
QuentinDuchemin, YohanndeCastro, ClaireLacour....
Published date-11/20/2020
We prove a new concentration inequality for U-statistics of order two for uniformly ergodic Markov chains. Working with bounded $\pi$-canonical kernels, we show that we can recover the convergence rate …
Robust super-resolution depth imaging via a multi-feature fusion deep network
AliceRuget, StephenMcLaughlin, RobertK.Henderson....
Published date-11/20/2020
AutonomousVehicles, Denoising, ImageDenoising, SuperResolution, Super-Resolution
Three-dimensional imaging plays an important role in imaging applications where it is necessary to record depth. The number of applications that use depth imaging is increasing rapidly, and examples include …
Assessing out-of-domain generalization for robust building damage detection
VitusBenson, AlexanderEcker....
Published date-11/20/2020
DomainGeneralization
An important step for limiting the negative impact of natural disasters is rapid damage assessment after a disaster occurred. For instance, building damage detection can be automated by applying computer …