paper-with-me

Papers

Effective Uncertainty Estimation with Evidential Models for Open-World Recognition

2021-09-29 · Charles Corbière, Marc Lafon, Nicolas Thome, Matthieu Cord, Patrick Perez

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.

📄 PDF Abstract BibTeX

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

2025-03-06 · Rohit Menon, Nils Dengler, Sicong Pan, Gokul Krishna Chenchani 외

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+2

Open Set Action Recognition via Multi-Label Evidential Learning

2023-02-27 · CVPR 2023 1 · Chen Zhao, Dawei Du, Anthony Hoogs, Christopher Funk

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 Recognition

Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation

2026-04-09 · Yongchan Chun, Chanhee Park, Jeongho Yoon, Jaehyung Seo 외 arxiv

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 Classification

EviNet: Evidential Reasoning Network for Resilient Graph Learning in the Open and Noisy Environments

2025-06-08 · Weijie Guan, Haohui Wang, Jian Kang, Lihui Liu 외

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 Detection

Evidential Uncertainty Estimation for Multi-Modal Trajectory Prediction

2025-03-07 · Sajad Marvi, Christoph Rist, Julian Schmidt, Julian Jordan 외

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