mlsanityData to 14 Oct 2026

Prior Distribution and Model Confidence

arXiv 2509.05485 ↗First posted 5 Sep 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

We study how the training data distribution affects confidence and performance in image classification models. We introduce Embedding Density, a model-agnostic framework that estimates prediction confidence by measuring the distance of test samples from the training distribution in embedding space, without requiring retraining. By filtering low-density (low-confidence) predictions, our method significantly improves classification accuracy. We evaluate Embedding Density across multiple architectures and compare it with state-of-the-art out-of-distribution (OOD) detection methods. The proposed approach is potentially generalizable beyond computer vision.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 51 of its 73 references that are in the map. First posted on arXiv 5 Sep 2025.

Builds on

51 of 73 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  8. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  9. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  10. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  11. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,516
  12. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
38 more
  1. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  2. 2016Concrete Problems in AI Safetycited by 1,642
  3. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  4. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  5. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  7. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  8. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  9. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  10. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  11. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  12. 2021Domain Generalization: A Surveycited by 764
  13. 2023DataComp: In search of the next generation of multimodal datasetscited by 644
  14. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  15. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  16. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 580
  17. 2015Towards Open Set Deep Networkscited by 538
  18. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  19. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  20. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  21. 2020Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamicscited by 425
  22. 2019Confident Learning: Estimating Uncertainty in Dataset Labelscited by 413
  23. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  24. 2023Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuningcited by 173
  25. 2022Training Data Influence Analysis and Estimation: A Surveycited by 135
  26. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  27. 2024Reducing hallucination in structured outputs via Retrieval-Augmented Generationcited by 93
  28. 2024Multi-Object Hallucination in Vision-Language Modelscited by 60
  29. 2023PanGu-Sigma: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computingcited by 56
  30. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 26
  31. 2023Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothnesscited by 15
  32. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  33. 2023Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspectivecited by 10
  34. 2024Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuningcited by 10
  35. 2022A Survey of Dataset Refinement for Problems in Computer Vision Datasetscited by 5
  36. 2025Learning Like Humans: Resource-Efficient Federated Fine-Tuning through Cognitive Developmental Stagescited by 4
  37. 2024FlowCon: Out-of-Distribution Detection using Flow-Based Contrastive Learningcited by 2
  38. 2017TokTrack: A Complete Token Provenance and Change Tracking Dataset for the English Wikipediacited by 1

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DR-SNE: Density-Regularized Stochastic Neighbor Embeddingcited by 0