Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation

• URL: http://arxiv.org/abs/2303.06920v2
• Date: Wed, 17 Jan 2024 08:35:13 GMT
• Title: Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation
• Authors: Kira Maag and Tobias Riedlinger
• Abstract summary: We present a method for obtaining uncertainty scores from pixel-wise loss gradients which can be computed efficiently during inference. Our experiments show the ability of our method to identify wrong pixel classifications and to estimate prediction quality at negligible computational overhead.
• Score: 0.43512163406552007
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, deep neural networks have defined the state-of-the-art in semantic segmentation where their predictions are constrained to a predefined set of semantic classes. They are to be deployed in applications such as automated driving, although their categorically confined expressive power runs contrary to such open world scenarios. Thus, the detection and segmentation of objects from outside their predefined semantic space, i.e., out-of-distribution (OoD) objects, is of highest interest. Since uncertainty estimation methods like softmax entropy or Bayesian models are sensitive to erroneous predictions, these methods are a natural baseline for OoD detection. Here, we present a method for obtaining uncertainty scores from pixel-wise loss gradients which can be computed efficiently during inference. Our approach is simple to implement for a large class of models, does not require any additional training or auxiliary data and can be readily used on pre-trained segmentation models. Our experiments show the ability of our method to identify wrong pixel classifications and to estimate prediction quality at negligible computational overhead. In particular, we observe superior performance in terms of OoD segmentation to comparable baselines on the SegmentMeIfYouCan benchmark, clearly outperforming other methods.

Related papers

• Anatomically-aware Uncertainty for Semi-supervised Image Segmentation [12.175556059523863]
  Semi-supervised learning relaxes the need of large pixel-wise labeled datasets for image segmentation by leveraging unlabeled data. Uncertainty estimation methods rely on multiple inferences from the model predictions that must be computed for each training step. This work proposes a novel method to estimate segmentation uncertainty by leveraging global information from the segmentation masks.
  arXiv  Detail & Related papers  (2023-10-24T18:03:07Z)
• NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation [87.50830107535533]
  Semi-supervised semantic segmentation involves assigning pixel-wise labels to unlabeled images at training time. Current approaches to semi-supervised semantic segmentation work by predicting pseudo-labels for each pixel from a class-wise probability distribution output by a model. In this work, we move one step forward by adapting NPs to semi-supervised semantic segmentation, resulting in a new model called NP-SemiSeg.
  arXiv  Detail & Related papers  (2023-08-05T12:42:15Z)
• Towards Better Certified Segmentation via Diffusion Models [62.21617614504225]
  segmentation models can be vulnerable to adversarial perturbations, which hinders their use in critical-decision systems like healthcare or autonomous driving. Recently, randomized smoothing has been proposed to certify segmentation predictions by adding Gaussian noise to the input to obtain theoretical guarantees. In this paper, we address the problem of certifying segmentation prediction using a combination of randomized smoothing and diffusion models.
  arXiv  Detail & Related papers  (2023-06-16T16:30:39Z)
• NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks [151.03112356092575]
  We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
  arXiv  Detail & Related papers  (2022-02-07T12:30:45Z)
• Bayesian Graph Contrastive Learning [55.36652660268726]
  We propose a novel perspective of graph contrastive learning methods showing random augmentations leads to encoders. Our proposed method represents each node by a distribution in the latent space in contrast to existing techniques which embed each node to a deterministic vector. We show a considerable improvement in performance compared to existing state-of-the-art methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-12-15T01:45:32Z)
• Uncertainty Aware Proposal Segmentation for Unknown Object Detection [13.249453757295083]
  This paper proposes to exploit additional predictions of semantic segmentation models and quantifying its confidences. We use object proposals generated by Region Proposal Network (RPN) and adapt distance aware uncertainty estimation of semantic segmentation. The augmented object proposals are then used to train a classifier for known vs. unknown objects categories.
  arXiv  Detail & Related papers  (2021-11-25T01:53:05Z)
• On the Practicality of Deterministic Epistemic Uncertainty [106.06571981780591]
  deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution data. It remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications.
  arXiv  Detail & Related papers  (2021-07-01T17:59:07Z)
• Minimax Active Learning [61.729667575374606]
  Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either rely on model uncertainty to select the most uncertain samples or use clustering or reconstruction to choose the most diverse set of unlabeled examples. We develop a semi-supervised minimax entropy-based active learning algorithm that leverages both uncertainty and diversity in an adversarial manner.
  arXiv  Detail & Related papers  (2020-12-18T19:03:40Z)
• Probabilistic Deep Learning for Instance Segmentation [9.62543698736491]
  We propose a generic method to obtain model-inherent uncertainty estimates within proposal-free instance segmentation models. We evaluate our method on the BBBC010 C. elegans dataset, where it yields competitive performance.
  arXiv  Detail & Related papers  (2020-08-24T19:51:48Z)
• Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks [22.34227625637843]
  We investigate how the parametrization of the probabilities in discriminative classifiers affects the uncertainty estimates. We show that one-vs-all formulations can improve calibration on image classification tasks.
  arXiv  Detail & Related papers  (2020-07-10T01:55:02Z)
• Fine-grained Uncertainty Modeling in Neural Networks [0.0]
  We present a novel method to detect out-of-distribution points in a Neural Network. Our method corrects overconfident NN decisions, detects outlier points and learns to say I don't know'' when uncertain about a critical point between the top two predictions. As a positive side effect, our method helps to prevent adversarial attacks without requiring any additional training.
  arXiv  Detail & Related papers  (2020-02-11T05:06:25Z)

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.