paper-with-me

홈 › Papers

Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold

2022-07-01 · NAACL 2022 7 · Yanan Wu, Keqing He, Yuanmeng Yan, QiXiang Gao, Zhiyuan Zeng, Fujia Zheng, Lulu Zhao, Huixing Jiang, Wei Wu, Weiran Xu

Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. A key challenge of OOD detection is the overconfidence of neural models. In this paper, we comprehensively analyze overconfidence and classify it into two perspectives: over-confident OOD and in-domain (IND). Then according to intrinsic reasons, we respectively propose a novel reassigned contrastive learning (RCL) to discriminate IND intents for over-confident OOD and an adaptive class-dependent local threshold mechanism to separate similar IND and OOD intents for over-confident IND. Experiments and analyses show the effectiveness of our proposed method for both aspects of overconfidence issues.

📄 PDF Abstract BibTeX

Code (1)

pris-nlp/naacl2022-reassigned_contrastive_learning_ood 공식 구현 pytorch

Tasks

Contrastive LearningOut of Distribution (OOD) Detection

Similar Papers 제목 키워드 기반

eMargin: Revisiting Contrastive Learning with Margin-Based Separation

2025-07-20 · Abdul-Kazeem Shamba, Kerstin Bach, Gavin Taylor arxiv

We revisit previous contrastive learning frameworks to investigate the effect of introducing an adaptive margin into the contrastive loss function for time series representation learning. Specifically, we explore whether…

Representation LearningContrastive Learning

Simplification Is All You Need against Out-of-Distribution Overconfidence

2025-01-01 · CVPR 2025 1 · Keke Tang, Chao Hou, Weilong Peng, Xiang Fang 외

Deep neural networks (DNNs) often exhibit out-of-distribution (OOD) overconfidence, producing overly confident predictions on OOD samples. We attribute this issue to the inherent over-complexity of DNNs and investiga…

AllAttributeKnowledge Distillation

Mitigating Overconfidence in Out-of-Distribution Detection by Capturing Extreme Activations

2024-05-21 · Mohammad Azizmalayeri, Ameen Abu-Hanna, Giovanni Cinà

Detecting out-of-distribution (OOD) instances is crucial for the reliable deployment of machine learning models in real-world scenarios. OOD inputs are commonly expected to cause a more uncertain prediction in the primar…

Out-of-Distribution Detection

Towards Efficient and General-Purpose Few-Shot Misclassification Detection for Vision-Language Models

2025-03-26 · Fanhu Zeng, Zhen Cheng, Fei Zhu, Xu-Yao Zhang

Reliable prediction by classifiers is crucial for their deployment in high security and dynamically changing situations. However, modern neural networks often exhibit overconfidence for misclassified predictions, highlig…

Prompt Learning

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations

2021-06-10 · NeurIPS 2021 12 · Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Luc van Gool

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like …

Instance Segmentationobject-detectionObject DetectionRetrieval+3