paper-with-me

홈 › Papers

AP-OOD: Attention Pooling for Out-of-Distribution Detection

2026-02-05 · Claus Hofmann, Christian Huber, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter, Werner Zellinger arxiv

Out-of-distribution (OOD) detection, which maps high-dimensional data into a scalar OOD score, is critical for the reliable deployment of machine learning models. A key challenge in recent research is how to effectively leverage and aggregate token embeddings from language models to obtain the OOD score. In this work, we propose AP-OOD, a novel OOD detection method for natural language that goes beyond simple average-based aggregation by exploiting token-level information. AP-OOD is a semi-supervised approach that flexibly interpolates between unsupervised and supervised settings, enabling the use of limited auxiliary outlier data. Empirically, AP-OOD sets a new state of the art in OOD detection for text: in the unsupervised setting, it reduces the FPR95 (false positive rate at 95% true positives) from 27.84% to 4.67% on XSUM summarization, and from 77.08% to 70.37% on WMT15 En-Fr translation.

📄 PDF Abstract BibTeX arXiv:2602.06031

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Detection

Similar Papers 제목 키워드 기반

Distribution Based MIL Pooling Filters are Superior to Point Estimate Based Counterparts

2021-01-01 · Mustafa Umit Oner, Jared Marc Song, Hwee Kuan Lee, Wing-Kin Sung

Multiple instance learning (MIL) is a machine learning paradigm which learns the mapping between bags of instances and bag labels. There are different MIL tasks which can be solved by different MIL methods. One common co…

Multiple Instance Learning

Studying The Effect of MIL Pooling Filters on MIL Tasks

2020-06-02 · Mustafa Umit Oner, Jared Marc Song Kye-Jet, Hwee Kuan Lee, Wing-Kin Sung

There are different multiple instance learning (MIL) pooling filters used in MIL models. In this paper, we study the effect of different MIL pooling filters on the performance of MIL models in real world MIL tasks. We de…

AttributeMultiple Instance Learning

Temporal Attention Pooling for Frequency Dynamic Convolution in Sound Event Detection

2025-04-17 · Hyeonuk Nam, Yong-Hwa Park

Recent advances in deep learning, particularly frequency dynamic convolution (FDY conv), have significantly improved sound event detection (SED) by enabling frequency-adaptive feature extraction. However, FDY conv relies…

Event DetectionSound Event Detection

PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection

2024-08-26 · Yidi Li, Jiahao Wen, Bin Ren, Wenhao Li 외

The integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. However, this combination often struggles with capturing semantic information effectively. Moreover, relying …

3D Object DetectionObjectobject-detectionObject Detection

Context-Aware Feature-Fusion for Co-occurring Object Detection in Autonomous Driving

2026-06-10 · Binay Kumar Singh, Niels Da Vitoria Lobo arxiv

Object detection in autonomous driving requires precise localization and an inherent understanding of the relational context between co-occurring objects. In extremely complex heterogeneous environments rare classes, sma…

Small Object DetectionAutonomous Driving