Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models
Beyond assigning the correct class, an activity recognition model should also be able to determine, how certain it is in its predictions. We present the first study of how welthe confidence values of modern action recognition architectures indeed reflect the probability of the correct outcome and propose a learning-based approach for improving it. First, we extend two popular action recognition datasets with a reliability benchmark in form of the expected calibration error and reliability diagrams. Since our evaluation highlights that confidence values of standard action recognition architectures do not represent the uncertainty well, we introduce a new approach which learns to transform the model output into realistic confidence estimates through an additional calibration network. The main idea of our Calibrated Action Recognition with Input Guidance (CARING) model is to learn an optimal scaling parameter depending on the video representation. We compare our model with the native action recognition networks and the temperature scaling approach - a wide spread calibration method utilized in image classification. While temperature scaling alone drastically improves the reliability of the confidence values, our CARING method consistently leads to the best uncertainty estimates in all benchmark settings.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionActivity Recognitionimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition
Human Activity Recognition (HAR) has seen significant advancements with the adoption of deep learning techniques, yet challenges remain in terms of data requirements, reliability and robustness. This paper explores a nov…
Human Activity RecognitionSelf-Supervised LearningData AugmentationLabel Leakage in Federated Inertial-based Human Activity Recognition
While prior work has shown that Federated Learning updates can leak sensitive information, label reconstruction attacks, which aim to recover input labels from shared gradients, have not yet been examined in the context …
Activity RecognitionFederated LearningHuman Activity RecognitionBAR: Bayesian Activity Recognition using variational inference
Uncertainty estimation in deep neural networks is essential for designing reliable and robust AI systems. Applications such as video surveillance for identifying suspicious activities are designed with deep neural networ…
Activity RecognitionBayesian InferenceVariational InferenceUncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery
Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unknown contexts and activities may occur f…
Activity RecognitionClusteringHuman Activity RecognitionUncertainty QuantificationPrivacy and Utility Preserving Sensor-Data Transformations
Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications. To mitigate these threats, we propose mecha…
Activity Recognition