TRADI: Tracking deep neural network weight distributions for uncertainty estimation
arXiv:1912.11316
Abstract
During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function. Only this final state of the weights is typically kept for testing, while the wealth of information on the geometry of the weight space, accumulated over the descent towards the minimum is discarded. In this work we propose to make use of this knowledge and leverage it for computing the distributions of the weights of the DNN. This can be further used for estimating the epistemic uncertainty of the DNN by sampling an ensemble of networks from these distributions. To this end we introduce a method for tracking the trajectory of the weights during optimization, that does not require any changes in the architecture nor on the training procedure. We evaluate our method on standard classification and regression benchmarks, and on out-of-distribution detection for classification and semantic segmentation. We achieve competitive results, while preserving computational efficiency in comparison to other popular approaches.
arXiv commentAccepted to ECCV2020
References in corpus (19)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Auto-Encoding Variational Bayes
- Wide Residual Networks
- On Calibration of Modern Neural Networks
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Going Deeper with Convolutions
- Weight Uncertainty in Neural Networks
- ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
- Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
- Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks
- A Simple Baseline for Bayesian Uncertainty in Deep Learning
- Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
- Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation
- Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
- Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches
- LCA: Loss Change Allocation for Neural Network Training
- The Extended Kalman Filter is a Natural Gradient Descent in Trajectory Space