Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection
–Neural Information Processing Systems
Out-of-distribution (OOD) detection is essential for reliably deploying machine learning models in the wild. Yet, most methods treat large pre-trained models as monolithic encoders and rely solely on their final-layer representations for detection.
Neural Information Processing Systems
Jun-20-2026, 21:12:52 GMT
- Country:
- Europe (0.28)
- Genre:
- Research Report
- New Finding (1.00)
- Experimental Study (1.00)
- Research Report
- Industry:
- Information Technology > Security & Privacy (0.67)
- Technology:
- Information Technology
- Data Science > Data Mining (1.00)
- Sensing and Signal Processing (0.92)
- Artificial Intelligence
- Vision (1.00)
- Representation & Reasoning (1.00)
- Natural Language
- Large Language Model (0.93)
- Text Processing (0.67)
- Machine Learning
- Performance Analysis > Accuracy (1.00)
- Neural Networks (1.00)
- Information Technology