mlsanityData to 7 Oct 2026

Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning

arXiv 2206.09798 ↗First posted 20 Jun 2022cs.LG cs.IT math.ITcited by 0

Not on the map. Why?

Abstract (arXiv)

The success of deep active learning hinges on the choice of an effective acquisition function, which ranks not yet labeled data points according to their expected informativeness. Many acquisition functions are (partly) based on the uncertainty that the current model has about the class label of a point, yet there is no generally agreed upon strategy for computing such uncertainty. This paper proposes a new and very simple approach to computing uncertainty in deep active learning with a Convolutional Neural Network (CNN). The main idea is to use the feature representation extracted by the CNN as data for training a Sum-Product Network (SPN). Since SPNs are typically used for estimating the distribution of a dataset, they are well suited to the task of estimating class probabilities that can be used directly by standard acquisition functions such as max entropy and variational ratio. The effectiveness of our method is demonstrated in an experimental study on several standard benchmark datasets for image classification, where we compare it to various state-of-the-art methods for assessing uncertainty in deep active learning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 20 Jun 2022.

Builds on

18 of 37 references.

References · 18

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  7. 2017Deep Bayesian Active Learning with Image Datacited by 812
  8. 2020A Survey of Deep Active Learningcited by 547
  9. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  10. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 359
  11. 2019Variational Adversarial Active Learningcited by 284
  12. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 165
6 more
  1. 2022A Comparative Survey of Deep Active Learningcited by 88
  2. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
  3. 2019Rethinking deep active learning: Using unlabeled data at model trainingcited by 39
  4. 2022PT4AL: Using Self-Supervised Pretext Tasks for Active Learningcited by 27
  5. 2015On the Relationship between Sum-Product Networks and Bayesian Networkscited by 13
  6. 2018Probabilistic Deep Learning using Random Sum-Product Networkscited by 2

Built on by

Not cited yet.