Format Online paper / PDF "What counts as out of distribution partly depends on how the task defines familiar categories, semantic differences and relevant distribution shifts." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Crossing the Bounds Source title Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks Source authors Hongjun Wang, Sagar Vaze, Kai Han Source year 2024 Confidence high Importance high
Format Online paper / PDF "A detector can identify unfamiliar examples as unknown without immediately being able to name their categories." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Crossing the Bounds Source title Towards Open World Object Detection Source authors K J Joseph, Salman Khan, Fahad Shahbaz Khan, Vineeth N Balasubramanian Source year 2021 Confidence high Importance mid
Format Online paper / PDF "Even when a detector uses additional training data, it can retain blind spots associated with the unfamiliar cases used to develop and evaluate it." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Crossing the Bounds Source title Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks Source authors Hongjun Wang, Sagar Vaze, Kai Han Source year 2024 Confidence high Importance high
Format Online paper / PDF "OOD detection depends on assumptions about which unfamiliar distributions matter." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Crossing the Bounds Source title Understanding Failures in Out-of-Distribution Detection with Deep Generative Models Source authors Lily H. Zhang, Mark Goldstein, Rajesh Ranganath Source year 2021 Confidence high Importance high
Format Online paper / PDF "In narrow environments, OOD detection techniques can be genuinely useful when their assumptions and relevant operating conditions are sufficiently specified." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Crossing the Bounds Source title On the Learnability of Out-of-distribution Detection Source authors Zhen Fang, Yixuan Li, Feng Liu, Bo Han, Jie Lu Source year 2024 Confidence high Importance high
Format Online paper / PDF "Additional layers can try to detect out-of-distribution problems during runtime." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Crossing the Bounds Source title Efficient out-of-distribution detection via layer-adaptive scoring and early stopping Source authors Haoliang Wang, Chen Zhao, Feng Chen Source year 2024 Confidence high Importance high
Format Online paper / PDF "OOD detection in LLMs can be useful as a local engineering heuristic." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Crossing the Bounds Source title How Good Are LLMs at Out-of-Distribution Detection? Source authors Bo Liu, Li-Ming Zhan, Zexin Lu, Yujie Feng, Lei Xue, Xiao-Ming Wu Source year 2024 Confidence high Importance high
Format Web Page "You can compare several models and flag disagreement, or train a separate detector to recognize unfamiliar inputs." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Crossing the Bounds Source title What is Out-of-Distribution (OOD) Detection? Source authors Alexandre Bonnet Source year 2026 Confidence high Importance mid
Format Online paper / PDF "You can measure how far a new example sits from familiar ones to help detect out-of-distribution inputs." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Crossing the Bounds Source title How Good Are LLMs at Out-of-Distribution Detection? Source authors Bo Liu, Li-Ming Zhan, Zexin Lu, Yujie Feng, Lei Xue, Xiao-Ming Wu Source year 2024 Confidence high Importance mid
Format Online paper / PDF "You can watch for unusually low probabilities or high uncertainty to flag possible out-of-distribution inputs." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Crossing the Bounds Source title A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks Source authors Dan Hendrycks, Kevin Gimpel Source year 2017 Confidence high Importance mid
