A General and Adaptive Robust Loss Function
We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc, generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions. By introducing robustness as a continuous parameter, our loss function allows algorithms built around robust loss minimization to be generalized, which improves performance on basic vision tasks such as registration and clustering. Interpreting our loss as the negative log of a univariate density yields a general probability distribution that includes normal and Cauchy distributions as special cases. This probabilistic interpretation enables the training of neural networks in which the robustness of the loss automatically adapts itself during training, which improves performance on learning-based tasks such as generative image synthesis and unsupervised monocular depth estimation, without requiring any manual parameter tuning.
Code (3)
Tasks
ClusteringDepth EstimationImage GenerationUnsupervised Monocular Depth EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning
In few-shot learning scenarios, the challenge is to generalize and perform well on new unseen examples when only very few labeled examples are available for each task. Model-agnostic meta-learning (MAML) has gained the p…
Few-Shot LearningMeta-LearningLearning Adaptive Loss for Robust Learning with Noisy Labels
Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current robust loss functions, however, inevitably involve hyperparameter(s) to be tuned, manually or heuristically th…
Learning with noisy labelsMeta-LearningStochastic Runge-Kutta methods and adaptive SGD-G2 stochastic gradient descent
The minimization of the loss function is of paramount importance in deep neural networks. On the other hand, many popular optimization algorithms have been shown to correspond to some evolution equation of gradient flow …
Penalizing small errors using an Adaptive Logarithmic Loss
Loss functions are error metrics that quantify the difference between a prediction and its corresponding ground truth. Fundamentally, they define a functional landscape for traversal by gradient descent. Although numerou…
Image SegmentationMedical Image SegmentationRetinal Vessel SegmentationSegmentation+1Adaptive particle-based approximations of the Gibbs posterior for inverse problems
In this work, we adopt a general framework based on the Gibbs posterior to update belief distributions for inverse problems governed by partial differential equations (PDEs). The Gibbs posterior formulation is a generali…
Bayesian Inference