Mitigating Neural Network Overconfidence with Logit Normalization
This addresses a critical safety issue for deploying machine learning models in real-world scenarios by improving out-of-distribution detection, though it is an incremental improvement over existing methods.
The paper tackles the problem of neural network overconfidence, which hinders out-of-distribution detection, by introducing Logit Normalization (LogitNorm), a simple modification to the cross-entropy loss that enforces a constant logit norm during training, resulting in a reduction of the average FPR95 by up to 42.30% on benchmarks.
Detecting out-of-distribution inputs is critical for safe deployment of machine learning models in the real world. However, neural networks are known to suffer from the overconfidence issue, where they produce abnormally high confidence for both in- and out-of-distribution inputs. In this work, we show that this issue can be mitigated through Logit Normalization (LogitNorm) -- a simple fix to the cross-entropy loss -- by enforcing a constant vector norm on the logits in training. Our method is motivated by the analysis that the norm of the logit keeps increasing during training, leading to overconfident output. Our key idea behind LogitNorm is thus to decouple the influence of output's norm during network optimization. Trained with LogitNorm, neural networks produce highly distinguishable confidence scores between in- and out-of-distribution data. Extensive experiments demonstrate the superiority of LogitNorm, reducing the average FPR95 by up to 42.30% on common benchmarks.