Uncertainty estimation in Deep Learning for Panoptic segmentation
- URL: http://arxiv.org/abs/2304.02098v1
- Date: Tue, 4 Apr 2023 19:54:35 GMT
- Title: Uncertainty estimation in Deep Learning for Panoptic segmentation
- Authors: Michael Smith, Frank Ferrie
- Abstract summary: We show how ensemble-based uncertainty estimation approaches can be used in the panoptic segmentation domain.
Results are demonstrated on the COCO, KITTI-STEP and VIPER datasets.
- Score: 1.0062187787765149
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: As deep learning-based computer vision algorithms continue to improve and
advance the state of the art, their robustness to real-world data continues to
lag their performance on datasets. This makes it difficult to bring an
algorithm from the lab to the real world. Ensemble-based uncertainty estimation
approaches such as Monte Carlo Dropout have been successfully used in many
applications in an attempt to address this robustness issue. Unfortunately, it
is not always clear if such ensemble-based approaches can be applied to a new
problem domain. This is the case with panoptic segmentation, where the
structure of the problem and architectures designed to solve it means that
unlike image classification or even semantic segmentation, the typical solution
of using a mean across samples cannot be directly applied. In this paper, we
demonstrate how ensemble-based uncertainty estimation approaches such as Monte
Carlo Dropout can be used in the panoptic segmentation domain with no changes
to an existing network, providing both improved performance and more
importantly a better measure of uncertainty for predictions made by the
network. Results are demonstrated quantitatively and qualitatively on the COCO,
KITTI-STEP and VIPER datasets.
Related papers
- Revisiting Generative Adversarial Networks for Binary Semantic
Segmentation on Imbalanced Datasets [20.538287907723713]
Anomalous crack region detection is a typical binary semantic segmentation task, which aims to detect pixels representing cracks on pavement surface images automatically by algorithms.
Existing deep learning-based methods have achieved outcoming results on specific public pavement datasets, but the performance would deteriorate dramatically on imbalanced datasets.
We propose a deep learning framework based on conditional Generative Adversarial Networks (cGANs) for the anomalous crack region detection tasks at the pixel level.
arXiv Detail & Related papers (2024-02-03T19:24:40Z) - Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matching [39.959000340261625]
We propose to dig into uncertainty estimation for robust stereo matching.
An uncertainty-based pseudo-label is proposed to adapt the pre-trained model to the new domain.
Our method shows strong cross-domain, adapt, and joint generalization and obtains textbf1st place on the stereo task of Robust Vision Challenge 2020.
arXiv Detail & Related papers (2023-07-31T09:11:31Z) - Uncertainty Estimation by Fisher Information-based Evidential Deep
Learning [61.94125052118442]
Uncertainty estimation is a key factor that makes deep learning reliable in practical applications.
We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL)
In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
arXiv Detail & Related papers (2023-03-03T16:12:59Z) - Acquisition-invariant brain MRI segmentation with informative
uncertainties [3.46329153611365]
Post-hoc multi-site correction methods exist but have strong assumptions that often do not hold in real-world scenarios.
This body of work showcases such an algorithm, that can become robust to the physics of acquisition in the context of segmentation tasks.
We demonstrate that our method not only generalises to complete holdout datasets, preserving segmentation quality, but does so while also accounting for site-specific sequence choices.
arXiv Detail & Related papers (2021-11-07T13:58:04Z) - 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) - Accurate and Robust Feature Importance Estimation under Distribution
Shifts [49.58991359544005]
PRoFILE is a novel feature importance estimation method.
We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
arXiv Detail & Related papers (2020-09-30T05:29:01Z) - 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) - Differentiable Causal Discovery from Interventional Data [141.41931444927184]
We propose a theoretically-grounded method based on neural networks that can leverage interventional data.
We show that our approach compares favorably to the state of the art in a variety of settings.
arXiv Detail & Related papers (2020-07-03T15:19:17Z) - Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic
Segmentation [63.75774438196315]
Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data.
Most existing methods suffer from noticeable negative transfer resulting from either the error-prone discriminator network or the unreasonable teacher model.
We propose an uncertainty-aware consistency regularization method for cross-domain semantic segmentation.
arXiv Detail & Related papers (2020-04-19T15:30:26Z) - Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction.
We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data.
Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
arXiv Detail & Related papers (2020-03-10T03:10:41Z) - Focus on Semantic Consistency for Cross-domain Crowd Understanding [34.560447389853614]
Some domain adaptation algorithms try to liberate it by training models with synthetic data.
We found that a mass of estimation errors in the background areas impede the performance of the existing methods.
In this paper, we propose a domain adaptation method to eliminate it.
arXiv Detail & Related papers (2020-02-20T08:51:05Z)
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.