mlsanityData to 7 Oct 2026

Bridging In- and Out-of-distribution Samples for Their Better Discriminability

arXiv 2101.02500 ↗First posted 7 Jan 2021cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

This paper proposes a method for OOD detection. Questioning the premise of previous studies that ID and OOD samples are separated distinctly, we consider samples lying in the intermediate of the two and use them for training a network. We generate such samples using multiple image transformations that corrupt inputs in various ways and with different severity levels. We estimate where the generated samples by a single image transformation lie between ID and OOD using a network trained on clean ID samples. To be specific, we make the network classify the generated samples and calculate their mean classification accuracy, using which we create a soft target label for them. We train the same network from scratch using the original ID samples and the generated samples with the soft labels created for them. We detect OOD samples by thresholding the entropy of the predicted softmax probability. The experimental results show that our method outperforms the previous state-of-the-art in the standard benchmark tests. We also analyze the effect of the number and particular combinations of image corrupting transformations on the performance.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 37 of its 53 references that are in the map. First posted on arXiv 7 Jan 2021.

Builds on

37 of 53 references.

References · 37

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2016Wide Residual Networkscited by 3,057
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  12. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
25 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  3. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  4. 2019When Does Label Smoothing Help?cited by 985
  5. 2018Exploration by Random Network Distillationcited by 966
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  7. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  8. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
  9. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  10. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  11. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  12. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  13. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  14. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  15. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  16. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  17. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  18. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  19. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  20. 2018Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifierscited by 126
  21. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  22. 2018Lightweight Probabilistic Deep Networkscited by 77
  23. 2018Bayesian Uncertainty Estimation for Batch Normalized Deep Networkscited by 70
  24. 2019Novelty Detection Via Blurringcited by 24
  25. 2019Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similaritycited by 12

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 0; 2025: 1.

2 papers.

  1. 2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 65
  2. 2025BOOST: Out-of-Distribution-Informed Adaptive Sampling for Bias Mitigation in Stylistic Convolutional Neural Networkscited by 0