Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection
This addresses a critical issue for neural networks in open-world applications by stabilizing OOD detection, though it appears incremental as it builds on existing techniques like model averaging and pruning.
The paper tackles the problem of unstable out-of-distribution (OOD) detection performance during neural network training, proposing Average of Pruning (AoP) to mitigate overfitting and sharp variations, resulting in improved stability and performance across various datasets and architectures.
Detecting Out-of-distribution (OOD) inputs have been a critical issue for neural networks in the open world. However, the unstable behavior of OOD detection along the optimization trajectory during training has not been explored clearly. In this paper, we first find the performance of OOD detection suffers from overfitting and instability during training: 1) the performance could decrease when the training error is near zero, and 2) the performance would vary sharply in the final stage of training. Based on our findings, we propose Average of Pruning (AoP), consisting of model averaging and pruning, to mitigate the unstable behaviors. Specifically, model averaging can help achieve a stable performance by smoothing the landscape, and pruning is certified to eliminate the overfitting by eliminating redundant features. Comprehensive experiments on various datasets and architectures are conducted to verify the effectiveness of our method.