mlsanityData to 7 Oct 2026

Graceful Degradation and Related Fields

arXiv 2106.11119 ↗First posted 21 Jun 2021cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

When machine learning models encounter data which is out of the distribution on which they were trained they have a tendency to behave poorly, most prominently over-confidence in erroneous predictions. Such behaviours will have disastrous effects on real-world machine learning systems. In this field graceful degradation refers to the optimisation of model performance as it encounters this out-of-distribution data. This work presents a definition and discussion of graceful degradation and where it can be applied in deployed visual systems. Following this a survey of relevant areas is undertaken, novelly splitting the graceful degradation problem into active and passive approaches. In passive approaches, graceful degradation is handled and achieved by the model in a self-contained manner, in active approaches the model is updated upon encountering epistemic uncertainties. This work communicates the importance of the problem and aims to prompt the development of machine learning strategies that are aware of graceful degradation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 103 of its 153 references that are in the map. First posted on arXiv 21 Jun 2021.

Builds on

103 of 153 references.

References · 103

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  7. 2016Adversarial examples in the physical worldcited by 1,762
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  9. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  10. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  12. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
38 more
  1. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  2. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  3. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  4. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  5. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  6. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  7. 2016Learning to learn by gradient descent by gradient descentcited by 616
  8. 2019Three scenarios for continual learningcited by 610
  9. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  10. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  11. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  12. 2015Weight Uncertainty in Neural Networkscited by 554
  13. 2019Meta-Learning with Implicit Gradientscited by 523
  14. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  15. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  16. 2018Deep Learning for Classical Japanese Literaturecited by 415
  17. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
  18. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  19. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 359
  20. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  21. 2019Learning Loss for Active Learningcited by 335
  22. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
  23. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  24. 2016Domain Separation Networkscited by 317
  25. 2018How to train your MAMLcited by 306
  26. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  27. 2019Variational Adversarial Active Learningcited by 284
  28. 2019Continual learning with hypernetworkscited by 267
  29. 2019Zero-Shot Semantic Segmentationcited by 245
  30. 2019Hyperbolic Image Embeddingscited by 219
  31. 2016Learning to Optimizecited by 195
  32. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  33. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  34. 2020Understanding the Role of Training Regimes in Continual Learningcited by 177
  35. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
  36. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 163
  37. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  38. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140

50 most cited of 103 All 103 (JSON)

Built on by

Not cited yet.