Thinkback: Task-SpecificOut-of-Distribution Detection
arXiv:2107.06668
Abstract
The increased success of Deep Learning (DL) has recently sparked large-scale deployment of DL models in many diverse industry segments. Yet, a crucial weakness of supervised model is the inherent difficulty in handling out-of-distribution samples, i.e., samples belonging to classes that were not presented to the model at training time. We propose in this paper a novel way to formulate the out-of-distribution detection problem, tailored for DL models. Our method does not require fine tuning process on training data, yet is significantly more accurate than the state of the art for out-of-distribution detection.
References in corpus (10)
- Overcoming catastrophic forgetting in neural networks
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
- Deep Anomaly Detection with Outlier Exposure
- The Extreme Value Machine
- TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking
- Clustering with Deep Learning: Taxonomy and New Methods
- A Benchmark of Medical Out of Distribution Detection
- One-vs-Rest Network-based Deep Probability Model for Open Set Recognition