When Less Compute Is More: Adaptive Early Exit Improves Pretrained Outlier Detection
This first study of depth-adaptive early-exit for pretrained outlier detection models finds that exiting at the optimal intermediate layer can also improve detection performance on diverse real-world benchmarks by 4.7-7.3% on average, consistent across three distinct foundation models.
Tian-Yan Zhou, L. Akoglu
· 0 citations