Search Results for author:
Found 4 papers, 4 papers with code
ESVAE: An Efficient Spiking Variational Autoencoder with Reparameterizable Poisson Spiking Sampling
In this paper, we propose an efficient spiking variational autoencoder (ESVAE) that constructs an interpretable latent space distribution and design a reparameterizable spiking sampling method.
Human-Level Control through Directly-Trained Deep Spiking Q-Networks
Specifically, we propose a directly-trained deep spiking reinforcement learning architecture based on the Leaky Integrate-and-Fire (LIF) neurons and Deep Q-Network (DQN).
Self Attention Grid for Person Re-Identification
We apply a max filter operation to non-overlapping sub-regions on the high feature representation before element-wise multiplied with the output of the second branch.
Sparse Label Smoothing Regularization for Person Re-Identification
Finally, we assign a non-uniform label distribution to the generated samples and define a regularized loss function for training.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
