Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks
Discriminatively trained, deterministic neural networks are the de facto choice for classification problems. However, even though they achieve state-of-the-art results on in-domain test sets, they tend to be overconfident on out-of-distribution (OOD) data. For instance, ReLU networks - a popular class of neural network architectures - have been shown to almost always yield high confidence predictions when the test data are far away from the training set, even when they are trained with OOD data. We overcome this problem by adding a term to the output of the neural network that corresponds to the logit of an extra class, that we design to dominate the logits of the original classes as we move away from the training data.This technique provably prevents arbitrarily high confidence on far-away test data while maintaining a simple discriminative point-estimate training. Evaluation on various benchmarks demonstrates strong performance against competitive baselines on both far-away and realistic OOD data.
Code (1)
Similar Papers 제목 키워드 기반
Towards neural networks that provably know when they don't know
It has recently been shown that ReLU networks produce arbitrarily over-confident predictions far away from the training data. Thus, ReLU networks do not know when they don't know. However, this is a highly important prop…
Out-of-Distribution DetectionWhy ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem
Classifiers used in the wild, in particular for safety-critical systems, should not only have good generalization properties but also should know when they don't know, in particular make low confidence predictions far aw…
General ClassificationBeing Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
The point estimates of ReLU classification networks---arguably the most widely used neural network architecture---have been shown to yield arbitrarily high confidence far away from the training data. This architecture, i…
Bayesian InferenceAnalysis of Confident-Classifiers for Out-of-distribution Detection
Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avo…
General Classificationimage-classificationImage ClassificationOut-of-Distribution Detection+1Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces
Traditional metasurface design is limited by the computational cost of full-wave simulations, preventing thorough exploration of complex configurations. Data-driven approaches have emerged as a solution to this bottlenec…