Trust, but Verify: Robust Image Segmentation using Deep Learning
- URL: http://arxiv.org/abs/2310.16999v3
- Date: Tue, 19 Dec 2023 22:29:46 GMT
- Title: Trust, but Verify: Robust Image Segmentation using Deep Learning
- Authors: Fahim Ahmed Zaman, Xiaodong Wu, Weiyu Xu, Milan Sonka and Raghuraman
Mudumbai
- Abstract summary: We describe a method for verifying the output of a deep neural network for medical image segmentation.
We show that previous methods for segmentation evaluation that do use deep neural regression networks are vulnerable to false negatives.
- Score: 7.220625464268644
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We describe a method for verifying the output of a deep neural network for
medical image segmentation that is robust to several classes of random as well
as worst-case perturbations i.e. adversarial attacks. This method is based on a
general approach recently developed by the authors called "Trust, but Verify"
wherein an auxiliary verification network produces predictions about certain
masked features in the input image using the segmentation as an input. A
well-designed auxiliary network will produce high-quality predictions when the
input segmentations are accurate, but will produce low-quality predictions when
the segmentations are incorrect. Checking the predictions of such a network
with the original image allows us to detect bad segmentations. However, to
ensure the verification method is truly robust, we need a method for checking
the quality of the predictions that does not itself rely on a black-box neural
network. Indeed, we show that previous methods for segmentation evaluation that
do use deep neural regression networks are vulnerable to false negatives i.e.
can inaccurately label bad segmentations as good. We describe the design of a
verification network that avoids such vulnerability and present results to
demonstrate its robustness compared to previous methods.
Related papers
- SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract.
We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
arXiv Detail & Related papers (2024-07-23T20:34:23Z) - Leveraging Unlabeled Data for 3D Medical Image Segmentation through
Self-Supervised Contrastive Learning [3.7395287262521717]
Current 3D semi-supervised segmentation methods face significant challenges such as limited consideration of contextual information.
We introduce two distinctworks designed to explore and exploit the discrepancies between them, ultimately correcting the erroneous prediction results.
We employ a self-supervised contrastive learning paradigm to distinguish between reliable and unreliable predictions.
arXiv Detail & Related papers (2023-11-21T14:03:16Z) - CNN-based Prediction of Network Robustness With Missing Edges [0.9239657838690227]
We investigate the performance of CNN-based approaches for connectivity and controllability prediction, when partial network information is missing.
A threshold is explored that if a total amount of more than 7.29% information is lost, the performance of CNN-based prediction will be significantly degenerated.
arXiv Detail & Related papers (2022-08-25T03:36:20Z) - Training on Test Data with Bayesian Adaptation for Covariate Shift [96.3250517412545]
Deep neural networks often make inaccurate predictions with unreliable uncertainty estimates.
We derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters.
We show that our method improves both accuracy and uncertainty estimation.
arXiv Detail & Related papers (2021-09-27T01:09:08Z) - False Negative Reduction in Video Instance Segmentation using
Uncertainty Estimates [0.0]
We present a false negative detection method for image sequences based on inconsistencies in time series of tracked instances.
As the number of instances can be greatly increased, we apply a false positive pruning using uncertainty estimates aggregated over instances.
The proposed method serves as a post-processing step applicable to any neural network that can also be trained on single frames only.
arXiv Detail & Related papers (2021-06-28T08:38:55Z) - DAAIN: Detection of Anomalous and Adversarial Input using Normalizing
Flows [52.31831255787147]
We introduce a novel technique, DAAIN, to detect out-of-distribution (OOD) inputs and adversarial attacks (AA)
Our approach monitors the inner workings of a neural network and learns a density estimator of the activation distribution.
Our model can be trained on a single GPU making it compute efficient and deployable without requiring specialized accelerators.
arXiv Detail & Related papers (2021-05-30T22:07:13Z) - Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators.
They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions.
We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
arXiv Detail & Related papers (2021-02-22T07:02:37Z) - Improving Video Instance Segmentation by Light-weight Temporal
Uncertainty Estimates [11.580916951856256]
We present a time-dynamic approach to model uncertainties of instance segmentation networks.
We apply this approach to the detection of false positives and the estimation of prediction quality.
The proposed method only requires a readily trained neural network and video sequence input.
arXiv Detail & Related papers (2020-12-14T13:39:05Z) - An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks.
We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem.
We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
arXiv Detail & Related papers (2020-12-06T18:55:07Z) - Collaborative Boundary-aware Context Encoding Networks for Error Map
Prediction [65.44752447868626]
We propose collaborative boundaryaware context encoding networks called AEP-Net for error prediction task.
Specifically, we propose a collaborative feature transformation branch for better feature fusion between images and masks, and precise localization of error regions.
The AEP-Net achieves an average DSC of 0.8358, 0.8164 for error prediction task, and shows a high Pearson correlation coefficient of 0.9873.
arXiv Detail & Related papers (2020-06-25T12:42:01Z) - Input Validation for Neural Networks via Runtime Local Robustness
Verification [3.4090949470658014]
We propose to validate inputs for neural networks via runtime local robustness verification.
Experiments show that our approach can protect neural networks from adversarial examples and improve their accuracies.
arXiv Detail & Related papers (2020-02-09T10:24:29Z)
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.