Search Results for author:
Found 6 papers, 0 papers with code
Real-Time Fully Unsupervised Domain Adaptation for Lane Detection in Autonomous Driving
While deep neural networks are being utilized heavily for autonomous driving, they need to be adapted to new unseen environmental conditions for which they were not trained.
Less is More: Data Pruning for Faster Adversarial Training
Deep neural networks (DNNs) are sensitive to adversarial examples, resulting in fragile and unreliable performance in the real world.
Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed
Recently, Diffenderfer and Kailkhura proposed a new paradigm for learning compact yet highly accurate binary neural networks simply by pruning and quantizing randomly weighted full precision neural networks.
Mixture of Robust Experts (MoRE):A Robust Denoising Method towards multiple perturbations
To tackle the susceptibility of deep neural networks to examples, the adversarial training has been proposed which provides a notion of robust through an inner maximization problem presenting the first-order embedded within the outer minimization of the training loss.
Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing
Federated learning is an emerging data-private distributed learning framework, which, however, is vulnerable to adversarial attacks.
Robust Decentralized Learning Using ADMM with Unreliable Agents
We also provide conditions on the erroneous updates for exact convergence to the optimal solution.
