Deep Deterministic Uncertainty for Semantic Segmentation

• URL: http://arxiv.org/abs/2111.00079v1
• Date: Fri, 29 Oct 2021 20:45:58 GMT
• Title: Deep Deterministic Uncertainty for Semantic Segmentation
• Authors: Jishnu Mukhoti, Joost van Amersfoort, Philip H.S. Torr, Yarin Gal
• Abstract summary: We extend Deep Deterministic Uncertainty (DDU) to semantic segmentation. We show that DDU improves upon MC Dropout and Deep Ensembles while being significantly faster to compute.
• Score: 97.89295891304394
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We extend Deep Deterministic Uncertainty (DDU), a method for uncertainty estimation using feature space densities, to semantic segmentation. DDU enables quantifying and disentangling epistemic and aleatoric uncertainty in a single forward pass through the model. We study the similarity of feature representations of pixels at different locations for the same class and conclude that it is feasible to apply DDU location independently, which leads to a significant reduction in memory consumption compared to pixel dependent DDU. Using the DeepLab-v3+ architecture on Pascal VOC 2012, we show that DDU improves upon MC Dropout and Deep Ensembles while being significantly faster to compute.

Related papers

• Single Image Depth Prediction Made Better: A Multivariate Gaussian Take [163.14849753700682]
  We introduce an approach that performs continuous modeling of per-pixel depth. Our method's accuracy (named MG) is among the top on the KITTI depth-prediction benchmark leaderboard.
  arXiv  Detail & Related papers  (2023-03-31T16:01:03Z)
• DDP: Diffusion Model for Dense Visual Prediction [71.55770562024782]
  We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. The method, called DDP, efficiently extends the denoising diffusion process into the modern perception pipeline. DDP shows attractive properties such as dynamic inference and uncertainty awareness, in contrast to previous single-step discriminative methods.
  arXiv  Detail & Related papers  (2023-03-30T17:26:50Z)
• DPVIm: Differentially Private Variational Inference Improved [13.761202518891329]
  Differentially private (DP) release of multidimensional statistics typically considers an aggregate sensitivity. Different dimensions of that vector might have widely different magnitudes and therefore DP perturbation disproportionately affects the signal across dimensions. We observe this problem in the gradient release of the DP-SGD algorithm when using it for variational inference (VI)
  arXiv  Detail & Related papers  (2022-10-28T07:41:32Z)
• Combating Mode Collapse in GANs via Manifold Entropy Estimation [70.06639443446545]
  Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications. We propose a novel training pipeline to address the mode collapse issue of GANs.
  arXiv  Detail & Related papers  (2022-08-25T12:33:31Z)
• RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation [27.679479140943503]
  We propose a resolution adaptive self-supervised monocular depth estimation method (RA-Depth) by learning the scale invariance of the scene depth. RA-Depth achieves state-of-the-art performance, and also exhibits a good ability of resolution adaptation.
  arXiv  Detail & Related papers  (2022-07-25T08:49:59Z)
• KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation [72.71398034617607]
  KERPLE is a framework that generalizes relative position embedding for extrapolation by kernelizing positional differences. The diversity of CPD kernels allows us to derive various RPEs that enable length extrapolation in a principled way.
  arXiv  Detail & Related papers  (2022-05-20T01:25:57Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Memory-based Deep Reinforcement Learning for POMDP [7.137228786549488]
  Long-Short-Term-Memory-based Twin Delayed Deep Deterministic Policy Gradient (LSTM-TD3) Our results demonstrate the significant advantages of the memory component in addressing Partially Observable MDPs.
  arXiv  Detail & Related papers  (2021-02-24T15:25:13Z)
• Unsupervised Discretization by Two-dimensional MDL-based Histogram [0.0]
  Unsupervised discretization is a crucial step in many knowledge discovery tasks. We propose an expressive model class that allows for far more flexible partitions of two-dimensional data. We introduce a algorithm, named PALM, which Partitions each dimension ALternately and then Merges neighboring regions.
  arXiv  Detail & Related papers  (2020-06-02T19:19:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.