Effective Uncertainty Estimation with Evidential Models for Open-World Recognition
Reliable uncertainty estimation is crucial when deploying a classifier in the wild. In this paper, we tackle the challenge of jointly quantifying in-distribution and out-of-distribution (OOD) uncertainties. To this end, we leverage the second-order uncertainty representation provided by evidential models and we introduce KLoS, a Kullback–Leibler divergence criterion defined on the class-probability simplex. By keeping the full distributional information, KLoS captures class confusion and lack of evidence in a single score. A crucial property of KLoS is to be a class-wise divergence measure built from in-distribution samples and to not require OOD training data, in contrast to current second-order uncertainty measures. We further design an auxiliary neural network, KLoSNet, to learn a refined criterion directly aligned with the evidential training objective. In the realistic context where no OOD data is available during training, our experiments show that KLoSNet outperforms first-order and second-order uncertainty measures to simultaneously detect misclassifications and OOD samples. When training with OOD samples, we also observe that existing measures are brittle to the choice of the OOD dataset, whereas KLoS remains more robust.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
EvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images
For scene understanding in unstructured environments, an accurate and uncertainty-aware metric-semantic mapping is required to enable informed action selection by autonomous systems. Existing mapping methods often suffer…
Depth EstimationDepth PredictionMulti-Task LearningScene Understanding+2Open Set Action Recognition via Multi-Label Evidential Learning
Existing methods for open-set action recognition focus on novelty detection that assumes video clips show a single action, which is unrealistic in the real world. We propose a new method for open set action recognition a…
Action DetectionAction RecognitionNovelty DetectionOpen Set Action RecognitionEvidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
Pretrained models have become standard in both vision and language, yet they typically do not provide reliable measures of confidence. Existing uncertainty estimation methods, such as deep ensembles and MC dropout, are o…
Image ClassificationEviNet: Evidential Reasoning Network for Resilient Graph Learning in the Open and Noisy Environments
Graph learning has been crucial to many real-world tasks, but they are often studied with a closed-world assumption, with all possible labels of data known a priori. To enable effective graph learning in an open and nois…
Graph LearningLogical ReasoningOut-of-Distribution DetectionEvidential Uncertainty Estimation for Multi-Modal Trajectory Prediction
Accurate trajectory prediction is crucial for autonomous driving, yet uncertainty in agent behavior and perception noise makes it inherently challenging. While multi-modal trajectory prediction models generate multiple p…
Autonomous DrivingPredictionTrajectory Prediction