AdaSCALE: Adaptive Scaling for OOD Detection
This work addresses the critical need for reliable OOD detection to ensure safe deployment of deep learning models, representing an incremental advance over existing activation shaping methods.
The paper tackles the problem of out-of-distribution (OOD) detection in deep learning by proposing AdaSCALE, an adaptive scaling method that dynamically adjusts thresholds based on sample likelihood, achieving state-of-the-art performance with improvements of 14.94% in near-OOD and 21.67% in far-OOD detection on ImageNet-1k.
The ability of the deep learning model to recognize when a sample falls outside its learned distribution is critical for safe and reliable deployment. Recent state-of-the-art out-of-distribution (OOD) detection methods leverage activation shaping to improve the separation between in-distribution (ID) and OOD inputs. These approaches resort to sample-specific scaling but apply a static percentile threshold across all samples regardless of their nature, resulting in suboptimal ID-OOD separability. In this work, we propose \textbf{AdaSCALE}, an adaptive scaling procedure that dynamically adjusts the percentile threshold based on a sample's estimated OOD likelihood. This estimation leverages our key observation: OOD samples exhibit significantly more pronounced activation shifts at high-magnitude activations under minor perturbation compared to ID samples. AdaSCALE enables stronger scaling for likely ID samples and weaker scaling for likely OOD samples, yielding highly separable energy scores. Our approach achieves state-of-the-art OOD detection performance, outperforming the latest rival OptFS by 14.94% in near-OOD and 21.67% in far-OOD datasets in average FPR@95 metric on the ImageNet-1k benchmark across eight diverse architectures. The code is available at: https://github.com/sudarshanregmi/AdaSCALE/