Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks

Code

• github.com/facebookresearch/odin
  OfficialIn paperpytorch★ 0
• github.com/remic-othr/openmibood
  pytorch★ 45
• github.com/jun-cen/unified_open_set_recognition
  pytorch★ 35
• github.com/kobybibas/pnml_ood_detection
  pytorch★ 25
• github.com/kingjamessong/rankfeat
  pytorch★ 20
• github.com/guyAmit/GLOD
  pytorch★ 16
• github.com/ShiyuLiang/odin-pytorch
  pytorch★ 0
• github.com/ericjang/odin
  pytorch★ 0
• github.com/JoonHyung-Park/ODIN
  pytorch★ 0

Abstract

We consider the problem of detecting out-of-distribution images in neural networks. We propose ODIN, a simple and effective method that does not require any change to a pre-trained neural network. Our method is based on the observation that using temperature scaling and adding small perturbations to the input can separate the softmax score distributions between in- and out-of-distribution images, allowing for more effective detection. We show in a series of experiments that ODIN is compatible with diverse network architectures and datasets. It consistently outperforms the baseline approach by a large margin, establishing a new state-of-the-art performance on this task. For example, ODIN reduces the false positive rate from the baseline 34.7% to 4.3% on the DenseNet (applied to CIFAR-10) when the true positive rate is 95%.

Tasks

Benchmark Results

Reproductions