Search Results for author:
Found 10 papers, 4 papers with code
VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representations
The recent increase in popularity of volumetric representations for scene reconstruction and novel view synthesis has put renewed focus on animating volumetric content at high visual quality and in real-time.
Offline Reinforcement Learning as Anti-Exploration
This is the converse of exploration in RL, which favors such actions.
Offline Reinforcement Learning with Pseudometric Learning
In the presence of function approximation, and under the assumption of limited coverage of the state-action space of the environment, it is necessary to enforce the policy to visit state-action pairs close to the support of logged transitions.
Information bottleneck through variational glasses
In particular, we present a new interpretation of VAE family based on the IB framework using a direct decomposition of mutual information terms and show some interesting connections to existing methods such as VAE [2; 3], beta-VAE [11], AAE [12], InfoVAE [5] and VAE/GAN [13].
$ρ$-VAE: Autoregressive parametrization of the VAE encoder
We make a minimal, but very effective alteration to the VAE model.
Robustification of deep net classifiers by key based diversified aggregation with pre-filtering
The robustness of the system is achieved by a specially designed key based randomization.
Reconstruction of Privacy-Sensitive Data from Protected Templates
In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA).
Defending against adversarial attacks by randomized diversification
The vulnerability of machine learning systems to adversarial attacks questions their usage in many applications.
Classification by Re-generation: Towards Classification Based on Variational Inference
We also introduce a criterion based on Kullback-Leibler divergence to reject doubtful examples.
Bridging machine learning and cryptography in defence against adversarial attacks
The majority of the proposed existing adversarial attacks are based on the differentiability of the DNN cost function. Defence strategies are mostly based on machine learning and signal processing principles that either try to detect-reject or filter out the adversarial perturbations and completely neglect the classical cryptographic component in the defence.
