Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?
We present an analysis of predictive uncertainty based out-of-distribution detection for different approaches to estimate various models' epistemic uncertainty and contrast it with extreme value theory based open set recognition. While the former alone does not seem to be enough to overcome this challenge, we demonstrate that uncertainty goes hand in hand with the latter method. This seems to be particularly reflected in a generative model approach, where we show that posterior based open set recognition outperforms discriminative models and predictive uncertainty based outlier rejection, raising the question of whether classifiers need to be generative in order to know what they have not seen.
Code (0)
등록된 구현이 없습니다.
Tasks
Open Set LearningOut-of-Distribution DetectionSimilar Papers 제목 키워드 기반
Gallery-Aware Uncertainty Estimation For Open-Set Face Recognition
Accurately estimating image quality and model robustness improvement are critical challenges in unconstrained face recognition, which can be addressed through uncertainty estimation via probabilistic face embeddings. Pre…
Face RecognitionFace VerificationOpen Set LearningWiOpen: A Robust Wi-Fi-based Open-set Gesture Recognition Framework
Recent years have witnessed a growing interest in Wi-Fi-based gesture recognition. However, existing works have predominantly focused on closed-set paradigms, where all testing gestures are predefined during training. Th…
Gesture RecognitionUncertainty QuantificationPlex: Towards Reliability using Pretrained Large Model Extensions
A recent trend in artificial intelligence is the use of pretrained models for language and vision tasks, which have achieved extraordinary performance but also puzzling failures. Probing these models' abilities in divers…
Active LearningDecision MakingmodelOpen Set LearningTest-time Similarity Modification for Person Re-identification toward Temporal Distribution Shift
Person re-identification (re-id), which aims to retrieve images of the same person in a given image from a database, is one of the most practical image recognition applications. In the real world, however, the environmen…
Person Re-IdentificationTest-time AdaptationEvaluating Uncertainty Calibration for Open-Set Recognition
Despite achieving enormous success in predictive accuracy for visual classification problems, deep neural networks (DNNs) suffer from providing overconfident probabilities on out-of-distribution (OOD) data. Yet, accurate…
Open Set Learning