Newest papers

Stochastic Nonlinearities Improve Uncertainty Estimation

Mohammad Sarhangzadeh, Amirreza M. Shebly, Doruk Öner · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29875 · cited by 0 works (OpenAlex) · open-access PDF

Korean

신뢰할 수 있는 불확실성 추정은 시각적 인식 작업을 통해 중요하며 모델 예측의 신뢰성과 신뢰성에 대한 정보를 제공합니다. 많은 효과적인 불확실성 추정 방법은 중간 기능을 억제하거나 입력을 방해하거나 상당한 추가 컴퓨팅을 요구할 수있는 메커니즘을 통해 예측 다양성을 얻습니다. 네트워크 유닛이 미리 통과하는 동안 여러 가지 비선형 인식 사이를 무작위로 선택하는 스토하스틱 활성화 기능은 이전에 최적화 동작을 개선하고 고정된 ReLU 활성화의 한계를 완화하고 출력 다양성을 증가시키는 데 사용되었습니다. 이 작업에서 우리는 불확실성 추정 메커니즘을 사용하여 불선형 활성화 기능 사이를 무작위로 선택합니다. 제안된

Machine translation (Meta M2M100); the English original follows.

Abstract

Reliable uncertainty estimation is important across visual recognition tasks, providing information about the confidence and reliability of model predictions. Many uncertainty estimation methods obtain predictive diversity through mechanisms that can suppress intermediate features, perturb the input, or require substantial additional computation. Stochastic activation functions, where network units randomly select between multiple nonlinearities during a forward pass, have previously been used to improve optimization behavior, mitigate limitations of fixed ReLU activations, and increase output diversity. In this work, we reframe stochastic activation switching as a lightweight mechanism for uncertainty estimation. The proposed method samples between nonlinear activation functions, inducing predictive diversity while keeping intermediate feature pathways active. This enables uncertainty estimation from a single trained model without the training cost of ensembles, task-specific uncertainty heads, or architectural redesign. We evaluate the proposed approach across classification, semantic segmentation, and out-of-distribution detection using convolutional and transformer-based architectures on diverse datasets. Across these settings, stochastic activation switching improves uncertainty quality while preserving competitive primary-task performance, showing that stochastic nonlinearities provide an effective and information-preserving source of predictive variation for visual recognition.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Reliability (semiconductor), Nonlinear system, Feature (linguistics), Stochastic process, Quality (philosophy)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange