SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection
It addresses OOD detection for object detection, an incremental improvement over existing methods.
The paper tackles out-of-distribution (OOD) detection in object detection by introducing Sensitivity-Aware Features (SAFE) from residual convolutional layers, which avoid the need for OOD training data or retraining, and achieves a 30.6% absolute reduction in FPR95 on the OpenImages dataset.
We address the problem of out-of-distribution (OOD) detection for the task of object detection. We show that residual convolutional layers with batch normalisation produce Sensitivity-Aware FEatures (SAFE) that are consistently powerful for distinguishing in-distribution from out-of-distribution detections. We extract SAFE vectors for every detected object, and train a multilayer perceptron on the surrogate task of distinguishing adversarially perturbed from clean in-distribution examples. This circumvents the need for realistic OOD training data, computationally expensive generative models, or retraining of the base object detector. SAFE outperforms the state-of-the-art OOD object detectors on multiple benchmarks by large margins, e.g. reducing the FPR95 by an absolute 30.6% from 48.3% to 17.7% on the OpenImages dataset.