mlsanityData to 14 Oct 2026

Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance

arXiv 2309.07403 ↗First posted 14 Sep 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

In real-world scenarios, typical visual recognition systems could fail under two major causes, i.e., the misclassification between known classes and the excusable misbehavior on unknown-class images. To tackle these deficiencies, flexible visual recognition should dynamically predict multiple classes when they are unconfident between choices and reject making predictions when the input is entirely out of the training distribution. Two challenges emerge along with this novel task. First, prediction uncertainty should be separately quantified as confusion depicting inter-class uncertainties and ignorance identifying out-of-distribution samples. Second, both confusion and ignorance should be comparable between samples to enable effective decision-making. In this paper, we propose to model these two sources of uncertainty explicitly with the theory of Subjective Logic. Regarding recognition as an evidence-collecting process, confusion is then defined as conflicting evidence, while ignorance is the absence of evidence. By predicting Dirichlet concentration parameters for singletons, comprehensive subjective opinions, including confusion and ignorance, could be achieved via further evidence combinations. Through a series of experiments on synthetic data analysis, visual recognition, and open-set detection, we demonstrate the effectiveness of our methods in quantifying two sources of uncertainties and dealing with flexible recognition.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 39 of its 52 references that are in the map. First posted on arXiv 14 Sep 2023.

Builds on

39 of 52 references.

References · 39

  1. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  4. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  5. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  6. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  7. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  8. 2015Towards Open Set Deep Networkscited by 538
  9. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  10. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  11. 2020Asymmetric Loss For Multi-Label Classificationcited by 381
  12. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 366
27 more
  1. 2019Deep Evidential Regressioncited by 355
  2. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 280
  3. 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 231
  4. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  5. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 210
  6. 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171
  7. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 164
  8. 2019Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentationcited by 163
  9. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
  10. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  11. 2020Hyperparameter Ensembles for Robustness and Uncertainty Quantificationcited by 150
  12. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  13. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  14. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  15. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
  16. 2014A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Inputcited by 112
  17. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  18. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  19. 2021Evidential Deep Learning for Open Set Action Recognitioncited by 96
  20. 2018Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Drivingcited by 90
  21. 2018Bayesian Layers: A Module for Neural Network Uncertaintycited by 57
  22. 2018Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Controlcited by 55
  23. 2020Few-Shot Open-Set Recognition using Meta-Learningcited by 50
  24. 2020Uncertainty-Aware Deep Classifiers using Generative Modelscited by 41
  25. 2019U-CAM: Visual Explanation using Uncertainty based Class Activation Mapscited by 36
  26. 2020Open-set Adversarial Defensecited by 27
  27. 2017Evidence combination for a large number of sourcescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 2; 2026: 1.

6 papers.

  1. 2023Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perceptioncited by 15
  2. 2024Revisiting Essential and Nonessential Settings of Evidential Deep Learningcited by 15
  3. 2024Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimationcited by 4
  4. 2025From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoningcited by 3
  5. 2026Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysiscited by 1
  6. 2025Open Set Face Forgery Detection via Dual-Level Evidence Collectioncited by 0