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 of 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 and Tiny-ImageNet) when the true positive rate is 95%. |
Year | Venue | Field |
---|---|---|
2018 | international conference on learning representations | False positive rate,Softmax function,Effective method,Image detection,Computer science,Network architecture,Artificial intelligence,Artificial neural network,True positive rate,Scaling,Machine learning |
DocType | Citations | PageRank |
Conference | 31 | 0.83 |
References | Authors | |
16 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shiyu Liang | 1 | 84 | 5.50 |
yixuan li | 2 | 43 | 9.08 |
Srikant, R. | 3 | 6868 | 544.90 |