mlsanityData to 7 Oct 2026

Predicted Embedding Power Regression for Large-Scale Out-of-Distribution Detection

arXiv 2303.04115 ↗First posted 7 Mar 2023cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) inputs can compromise the performance and safety of real world machine learning systems. While many methods exist for OOD detection and work well on small scale datasets with lower resolution and few classes, few methods have been developed for large-scale OOD detection. Existing large-scale methods generally depend on maximum classification probability, such as the state-of-the-art grouped softmax method. In this work, we develop a novel approach that calculates the probability of the predicted class label based on label distributions learned during the training process. Our method performs better than current state-of-the-art methods with only a negligible increase in compute cost. We evaluate our method against contemporary methods across 14 datasets and achieve a statistically significant improvement with respect to AUROC (84.2 vs 82.4) and AUPR (96.2 vs 93.7).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 7 Mar 2023.

Builds on

29 of 40 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2013Describing Textures in the Wildcited by 2,110
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  8. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  11. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  12. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
17 more
  1. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  2. 2021ImageNet-21K Pretraining for the Massescited by 607
  3. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  4. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  5. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  6. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  7. 2021Unsolved Problems in ML Safetycited by 291
  8. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  9. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  10. 2018Uncertainty in Neural Networks: Approximately Bayesian Ensemblingcited by 94
  11. 2022Anomaly Detection in Autonomous Driving: A Surveycited by 87
  12. 2017Hard Mixtures of Experts for Large Scale Weakly Supervised Visioncited by 67
  13. 2017Ensemble Samplingcited by 62
  14. 2018Discriminative out-of-distribution detection for semantic segmentationcited by 47
  15. 2019The reliability of a deep learning model in clinical out-of-distribution MRI data: a multicohort studycited by 38
  16. 2019Are Out-of-Distribution Detection Methods Effective on Large-Scale Datasets?cited by 6
  17. 2014Self-informed neural network structure learningcited by 3

Built on by

Not cited yet.