paper-with-me

홈 › Papers

A General and Adaptive Robust Loss Function

2017-01-11 · CVPR 2019 6 · Jonathan T. Barron

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.

📄 PDF Abstract BibTeX arXiv:1701.03077

Code (3)

google-research/google-research/tree/master/robust_loss 공식 구현 tf
andrewlstewart/StereoNet_PyTorch pytorch
jonbarron/robust_loss_pytorch pytorch

Tasks

ClusteringDepth EstimationImage GenerationUnsupervised Monocular Depth Estimation

Methods 이 논문이 사용한 방법론

Adaptive Loss 설명 없음

Similar Papers 제목 키워드 기반

Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning

2021-10-08 · ICCV 2021 10 · Sungyong Baik, Janghoon Choi, Heewon Kim, Dohee Cho 외

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-Learning

Learning Adaptive Loss for Robust Learning with Noisy Labels

2020-02-16 · Jun Shu, Qian Zhao, Keyu Chen, Zongben Xu 외

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-Learning

Stochastic Runge-Kutta methods and adaptive SGD-G2 stochastic gradient descent

2020-02-20 · Imen Ayadi, Gabriel Turinici

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

2019-10-22 · Chaitanya Kaul, Nick Pears, Hang Dai, Roderick Murray-Smith 외

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+1

Adaptive particle-based approximations of the Gibbs posterior for inverse problems

2019-07-02 · Zilong Zou, Sayan Mukherjee, Harbir Antil, Wilkins Aquino

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