mlsanityData to 7 Oct 2026

TRADI: Tracking deep neural network weight distributions for uncertainty estimation

arXiv 1912.11316 ↗First posted 24 Dec 2019cs.LG cs.CV stat.MLcited by 39

Not on the map. Why?

Abstract (arXiv)

During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function. Only this final state of the weights is typically kept for testing, while the wealth of information on the geometry of the weight space, accumulated over the descent towards the minimum is discarded. In this work we propose to make use of this knowledge and leverage it for computing the distributions of the weights of the DNN. This can be further used for estimating the epistemic uncertainty of the DNN by sampling an ensemble of networks from these distributions. To this end we introduce a method for tracking the trajectory of the weights during optimization, that does not require any changes in the architecture nor on the training procedure. We evaluate our method on standard classification and regression benchmarks, and on out-of-distribution detection for classification and semantic segmentation. We achieve competitive results, while preserving computational efficiency in comparison to other popular approaches.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 11; 2023: 11; 2024: 3; 2025: 4; 2026: 1.

39 papers.

Sort:

By area:

  1. 2022Packed-Ensembles for Efficient Uncertainty Estimationcited by 49
  2. 2022DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognitioncited by 42
  3. 2023PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awarenesscited by 42
  4. 2021Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentationcited by 40
  5. 2023Maskomaly:Zero-Shot Mask Anomaly Segmentationcited by 34
  6. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  7. 2021Robust Semantic Segmentation with Superpixel-Mixcited by 19
  8. 2023Mask2Anomaly: Mask Transformer for Universal Open-set Segmentationcited by 18
  9. 2021Dense outlier detection and open-set recognition based on training with noisy negative imagescited by 17
  10. 2022Latent Discriminant deterministic Uncertaintycited by 17
  11. 2023Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Modelscited by 15
  12. 2023A Symmetry-Aware Exploration of Bayesian Neural Network Posteriorscited by 12
27 more
  1. 2024Towards Understanding and Quantifying Uncertainty for Text-to-Image Generationcited by 11
  2. 2021Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Datacited by 10
  3. 2022C^*-algebra Net: A New Approach Generalizing Neural Network Parameters to C^*-algebracited by 9
  4. 2023Hybrid Open-set Segmentation with Synthetic Negative Datacited by 8
  5. 2023ProbVLM: Probabilistic Adapter for Frozen Vision-Language Modelscited by 7
  6. 2021A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statisticscited by 6
  7. 2023The Robust Semantic Segmentation UNCV2023 Challenge Resultscited by 5
  8. 2024Quantum-Cognitive Neural Networks: Assessing Confidence and Uncertainty with Human Decision-Making Simulationscited by 4
  9. 2025Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantificationcited by 4
  10. 2022Probing Contextual Diversity for Dense Out-of-Distribution Detectioncited by 3
  11. 2023Likelihood Annealing: Fast Calibrated Uncertainty for Regressioncited by 3
  12. 2025Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processescited by 3
  13. 2022Block Format Error Bounds and Optimal Block Size Selectioncited by 2
  14. 2022Statistical Modeling of Soft Error Influence on Neural Networkscited by 2
  15. 2022Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detectioncited by 2
  16. 2023Learning to Generate Training Datasets for Robust Semantic Segmentationcited by 2
  17. 2023Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executablescited by 2
  18. 2025Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNscited by 2
  19. 2024Partitioned Neural Network Training via Synthetic Intermediate Labelscited by 1
  20. 2021Intrinsic uncertainties and where to find themcited by 0
  21. 2021Learning a Discriminant Latent Space with Neural Discriminant Analysiscited by 0
  22. 2021Anomaly-Aware Semantic Segmentation by Leveraging Synthetic-Unknown Datacited by 0
  23. 2021Anomaly Discovery in Semantic Segmentation via Distillation Comparison Networkscited by 0
  24. 2022Instance-Aware Observer Network for Out-of-Distribution Object Segmentationcited by 0
  25. 2022Smooth Mathematical Function from Compact Neural Networkscited by 0
  26. 2025Efficient Continual Learning in Neural Machine Translation: A Low-Rank Adaptation Approachcited by 0
  27. 2026Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generationcited by 0