4 papers
Locally Linear Attributes of ReLU Neural Networks
Ben Sattelberg, Renzo Cavalieri, Michael Kirby +2
A ReLU neural network determines/is a continuous piecewise linear map from an input space to an output space. The weights in the neural network determine a decomposition of the inp…
Exploring the Interchangeability of CNN Embedding Spaces
David McNeely-White, Benjamin Sattelberg, Nathaniel Blanchard +1
CNN feature spaces can be linearly mapped and consequently are often interchangeable. This equivalence holds across variations in architectures, training datasets, and network task…
A Pose Proposal and Refinement Network for Better Object Pose Estimation
Ameni Trabelsi, Mohamed Chaabane, Nathaniel Blanchard +1
In this paper, we present a novel, end-to-end 6D object pose estimation method that operates on RGB inputs. Our approach is composed of 2 main components: the first component class…
Looking Ahead: Anticipating Pedestrians Crossing with Future Frames Prediction
Mohamed Chaabane, Ameni Trabelsi, Nathaniel Blanchard +1
In this paper, we present an end-to-end future-prediction model that focuses on pedestrian safety. Specifically, our model uses previous video frames, recorded from the perspective…