mlsanityData to 14 Oct 2026

Out-of-Distribution Detection with Adaptive Top-K Logits Integration

arXiv 2507.00368 ↗First posted 1 Jul 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural networks often make overconfident predictions from out-of-distribution (OOD) samples. Detection of OOD data is therefore crucial to improve the safety of machine learning. The simplest and most powerful method for OOD detection is MaxLogit, which uses the model's maximum logit to provide an OOD score. We have discovered that, in addition to the maximum logit, some other logits are also useful for OOD detection. Based on this finding, we propose a new method called ATLI (Adaptive Top-k Logits Integration), which adaptively determines effective top-k logits that are specific to each model and combines the maximum logit with the other top-k logits. In this study we evaluate our proposed method using ImageNet-1K benchmark. Extensive experiments showed our proposed method to reduce the false positive rate (FPR95) by 6.73% compared to the MaxLogit approach, and decreased FPR95 by an additional 2.67% compared to other state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

25 of 33 references.

References · 25

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  5. 2013Describing Textures in the Wildcited by 2,125
  6. 2019Searching for MobileNetV3cited by 1,994
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  8. 2019Natural Adversarial Examplescited by 1,408
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  11. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  12. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
13 more
  1. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 691
  2. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  5. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 431
  6. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  7. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  8. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  9. 2023Non-Parametric Outlier Synthesiscited by 129
  10. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
  11. 2022Block Selection Method for Using Feature Norm in Out-of-distribution Detectioncited by 30
  12. 2022A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptionscited by 6
  13. 2024Logit Scaling for Out-of-Distribution Detectioncited by 3

Built on by

Not cited yet.