Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Data

• URL: http://arxiv.org/abs/2402.17653v1
• Date: Tue, 27 Feb 2024 16:23:11 GMT
• Title: Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Data
• Authors: David S. W. Williams, Daniele De Martini, Matthew Gadd and Paul Newman
• Abstract summary: This work presents a segmentation network that can detect errors caused by challenging test domains without any additional annotation in a single forward pass. We use easy-to-obtain, uncurated and unlabelled data to learn to perform uncertainty estimation selectively by enforcing consistency over data augmentation. The proposed method, named Gamma-SSL, consistently outperforms uncertainty estimation and Out-of-Distribution (OoD) techniques on this difficult benchmark.
• Score: 19.000718685399935
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowing when a trained segmentation model is encountering data that is different to its training data is important. Understanding and mitigating the effects of this play an important part in their application from a performance and assurance perspective - this being a safety concern in applications such as autonomous vehicles (AVs). This work presents a segmentation network that can detect errors caused by challenging test domains without any additional annotation in a single forward pass. As annotation costs limit the diversity of labelled datasets, we use easy-to-obtain, uncurated and unlabelled data to learn to perform uncertainty estimation by selectively enforcing consistency over data augmentation. To this end, a novel segmentation benchmark based on the SAX Dataset is used, which includes labelled test data spanning three autonomous-driving domains, ranging in appearance from dense urban to off-road. The proposed method, named Gamma-SSL, consistently outperforms uncertainty estimation and Out-of-Distribution (OoD) techniques on this difficult benchmark - by up to 10.7% in area under the receiver operating characteristic (ROC) curve and 19.2% in area under the precision-recall (PR) curve in the most challenging of the three scenarios.

Related papers

• Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations [0.0]
  We introduce the notion of "label convergence" to describe the highest achievable performance under the constraint of contradictory test annotations. We approximate that label convergence is between 62.63-67.52 mAP@[0.5:0.95:0.05] for LVIS with 95% confidence, attributing these bounds to the presence of real annotation errors. With current state-of-the-art (SOTA) models at the upper end of the label convergence interval for the well-studied LVIS dataset, we conclude that model capacity is sufficient to solve current object detection problems.
  arXiv  Detail & Related papers  (2024-09-14T10:59:25Z)
• Downstream-Pretext Domain Knowledge Traceback for Active Learning [138.02530777915362]
  We propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. Experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-20T01:34:13Z)
• Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling [19.000718685399935]
  This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation models and unlabelled datasets through a Masked Image Modeling (MIM) approach. For neural networks used in safety-critical applications, bias in the training data can lead to errors.
  arXiv  Detail & Related papers  (2024-02-27T15:49:54Z)
• Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object Detection [3.7398615061365206]
  Federated Learning (FL) has emerged as a potent framework for training models across distributed data sources. It faces challenges with limited high-quality labels and non-IID client data, particularly in applications like autonomous driving. We present a pioneering SSFOD framework, designed for scenarios where labeled data reside only at the server while clients possess unlabeled data.
  arXiv  Detail & Related papers  (2023-10-26T01:40:28Z)
• Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning [69.81438976273866]
  Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers) We introduce evidential deep learning (EDL) as an outlier detector to quantify different types of uncertainty, and design different uncertainty metrics for self-training and inference. We propose a novel adaptive negative optimization strategy, making EDL more tailored to the unlabeled dataset containing both inliers and outliers.
  arXiv  Detail & Related papers  (2023-03-21T09:07:15Z)
• Uncertainty Reduction for 3D Point Cloud Self-Supervised Traversability Estimation [17.193700394066266]
  Self-supervised traversability estimation suffers from congenital uncertainties that appear according to the scarcity of negative information. We introduce a method to incorporate unlabeled data in order to leverage the uncertainty. We evaluate our approach on our own dataset, Dtrail', which is composed of a wide variety of negative data.
  arXiv  Detail & Related papers  (2022-11-21T06:24:41Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection [85.11649974840758]
  3D object detection networks tend to be biased towards the data they are trained on. We propose a single-frame approach for source-free, unsupervised domain adaptation of lidar-based 3D object detectors.
  arXiv  Detail & Related papers  (2021-11-30T18:42:42Z)
• A new weakly supervised approach for ALS point cloud semantic segmentation [1.4620086904601473]
  We propose a deep-learning based weakly supervised framework for semantic segmentation of ALS point clouds. We exploit potential information from unlabeled data subject to incomplete and sparse labels. Our method achieves an overall accuracy of 83.0% and an average F1 score of 70.0%, which have increased by 6.9% and 12.8% respectively.
  arXiv  Detail & Related papers  (2021-10-04T14:00:23Z)
• Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification [137.9939571408506]
  We estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels. Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2020-12-16T04:09:04Z)
• Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training [55.824641135682725]
  Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD show that up to 80% of the performance of a system trained on ground-truth data can be recovered.
  arXiv  Detail & Related papers  (2020-11-26T18:51:26Z)

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.