Open-Set Recognition

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 40

All topics

SmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing
Oct 1, 2026Thiru Thillai Nadarasar Bahavan, Yu Xia, Sachith Seneviratne +1Open-Set Recognition Smoothing
The University of Melbourne Parkville, VIC, Australia
Mixed-Prior Decision Risk for Open-Set Recognition
Sep 28, 2026L. A. Erlygin, P. D. Proskura, A. A. ZaytsevOpen-Set Recognition Uncertainty Score
Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia · Risk Management, Sber, Moscow, Russia · The Institute for Information Transmission Problems (IITP RAS), Moscow, Russia
Hyperbolic Geometry for Open-World Object Detection in Remote Sensing Imagery
Sep 10, 2026Wuzhou Li, Jiawei Zhou, Shenghang Wang +1Remote Sensing Object Detection
School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan 430072, China · Electronic Information School, Wuhan University, Wuhan 430072, China · Electrical and Computer Engineering, Ohio State University, Columbus, OH, USA +1
Open-Set Vessel Re-Identification from Underwater Ship-Radiated Noise with a Raw-Waveform Selective-Kernel Acoustic Neural Network (SKANN) and a Cross-Passage Evaluation Protocol
Sep 7, 2026Sunil TyagiShip Detection Underwater Acoustic Target Recognition
Oravont Systems LLP, Noida, India
OSR: Output Space Redistribution for Adaptive Label Removal in Classification Models
Sep 3, 2026Minyi Peng, Darian Gunamardi, Ivan Tjuawinata +2Label Propagation Classifier
Nanyang Technological University, 50 Nanyang Ave, Singapore, 639798
Class Geometry as Supervision for Sample-Efficient Open-World Detection
Aug 13, 2026Akash Rao, Zhou Chen, Revanth Reddy Palem +3Open-Vocabulary Object Detection Open-Set Recognition
CSSE Department, Auburn University, Auburn, AL, 36849 · Department of Veterinary Pathobiology, Oklahoma State University, Stillwater, OK, 74078
One-Time Training for All Grains: Open-Set Grain Recognition and Quantitative Analysis
Aug 10, 2026Qihe Su, Mengyu Sun, Yuxi Ke +4Precision Agriculture Fine-Grained Perception
National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Hubei Hongshan Laboratory, Huazhong Agricultural University, Wuhan, 430070, China · College of Engineering, Huazhong Agricultural University, Wuhan, 430070, China · Engineering Research Center of Intelligent Technology for Agriculture, Ministry of Education +1
Open-World Semantic Segmentation with Sensitivity Modeling
Aug 8, 2026Anastasios Romanos Varvarigos, Nikos Giakoumoglou, Tania StathakiEfficient Semantic Segmentation Semantic Segmentation
Department of Electrical and Electronic Engineering, Imperial College London, London, UK
Open-World Hierarchical Perception: Taxonomic Abstraction over Class-Agnostic Proposals for the Safe Handling of Out-of-Vocabulary Road Objects
Aug 4, 2026Felix SchallerAutonomous Driving Perception Open-Vocabulary Object Detection
Dubai, UAE / Munich, Germany
Tactus: Open-Vocabulary Object Recognition from Low-Cost Pressure Arrays
Aug 4, 2026Abdul Basit TonmoyTactile Hand Gesture Recognition
Eximius Labs Wabash College
Calibrated Similarity and Graph Clustering for Open-Set Animal Re-Identification
Aug 3, 2026Mohamed ElBassat, Seifeldin Elkerdany, Mohamed ElBialy +5Animal Re-Identification Open-Set Recognition
Made In Alexandria Artificial Intelligence Team, Alexandria, Egypt · Faculty of Computers and Data Science, Alexandria University, Alexandria, Egypt · Faculty of Computer Science and Engineering, Alamein International University, New Alamein City, 51718, Egypt +3
MarkushGlyph and OCSRGlyph: Improved Chemical Structure Recognition
Jul 30, 2026Alex Andonian, Samuel G Rodriques, Andrew D White +1Optical Character Recognition Image-Text Pairs
1Edison Scientific
Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
Jul 29, 2026Tianyan Deng, Yanxiong Li, Rui Gao +1Open-Set Recognition Transductive Learning
School of Mathematics South China University of Technology Guangzhou, China · School of Electronic and Information Engineering South China University of Technology Guangzhou, China
Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$
Jul 23, 2026Dawei Li, Xiaotian Jiang, Mingyi HongConvergence Newton
University of Minnesota
Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesis
Jul 6, 2026Zhipeng Xu, Zulong Chen, Qing Liu +6Information Extraction Large Multimodal Models
Alibaba Group · Taobao and Tmall Group, Alibaba · Qwen Team, Alibaba Group +1
Open-Set Source Tracing as Compositional Factors via Structured Prototypes
Jul 3, 2026Santiago Rubio, Antonio Almudévar, Antonio Miguel +2Speech Separation Open-Set Recognition
ViVoLab, I3A University of Zaragoza Zaragoza, Spain
GROW $^2$ : Grounding Which and Where for Robot Tool Use
Jun 29, 2026Yuhong Deng, Yuyao Liu, David HsuAffordances Robotic Systems
1National University of Singapore · 2Massachusetts Institute of Technology
Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios
Jun 22, 2026Xiran Wang, Jian Zhang, Lei Qi +2Multimodal Domain Generalization Open-Set Recognition
State Key Laboratory for Novel Software Technology, Nanjing University, China · School of Computer Science and Engineering, Southeast University, China
CITADEL: CSI-Based Jamming Detection and Open-Set Classification for IIoT Networks
Jun 22, 2026Aymen Bouferroum, Ildi Alla, Valeria Loscri +2Internet Of Thing Intentional Jamming
FUN · Inria Lille-Nord Europe, Lille, France · uni.lu +3
Quantum-Enhanced Similarity Measures for Polarimetric Materials Classification
Jun 5, 2026Sara Shojaei, Seyed Mohamad Ali Tousi, Emma Bennett +6Hybrid Quantum-Classical Pipeline Materials
University of Missouri–Columbia, MO, USA · Saint Louis University, MO, USA
High-Precision APT Malware Attribution with Out-of-Scope Resilience
Jun 2, 2026Peter Williams, Adam Sobey, Erisa KarafiliMalware Open-Set Recognition
University of Southampton, Southampton, UK · The Alan Turing Institute, London, UK
A Closer Look at In-Distribution vs. Out-of-Distribution Accuracy for Open-Set Test-time Adaptation
Jun 1, 2026Zefeng Li, Evan ShelhamerOut-Of-Distribution Detection Out-Of-Distribution
University of British Columbia and Vector Institute
Beyond the Simplex: Balanced Prototype Geometry for Scorer-Agnostic Open-Set Recognition
Jun 1, 2026Mayank Sharma, Rohit Kumar MouryaOpen-Set Recognition Simplex
Indian Institute of Technology Jodhpur
SCOPE: A Lightweight-training LLM Framework for Air Traffic Control Readback Monitoring
May 28, 2026Qihan Deng, Minghua Zhang, Yang Yang +1Air Traffic Control Pilot
Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, 999077, Hong Kong · School of Electronic and Information Engineering, Beihang University, Beijing, 100191, China · State Key Laboratory of CNS/ATM, Beijing, 100191, China
3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation
May 26, 2026Jianzhe Gao, Rui Liu, Wenguan WangVision-Language Navigation 3D Scene Understanding
The State Key Lab of Brain-Machine Intelligence, Zhejiang University
Lowering the Barrier to IREX Participation: Open-Source Algorithms, Toolkit, and Benchmarking for Iris Recognition
May 20, 2026Siamul Karim Khan, Patrick J. Flynn, Adam CzajkaOpen-Set Recognition Computer Vision
Department of Computer Science and Engineering, University of Notre Dame, Indiana, USA · University of Notre Dame, Indiana, USA
Evidence-Guided Unknown Rejection for High-Confidence Near-Known Unknowns
May 18, 2026Xi Chen, Yingjun Xiao, Gang FangRejection Open-Set Recognition
School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China · School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 510006, China · School of Artificial Intelligence, Guangzhou University, Guangzhou, China +3
When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
May 18, 2026Ningkang Peng, Jingyang Mao, Runhan Zhou +2Noisy Labels Out-Of-Distribution
Nanjing Normal University
Community-aware evaluation and threshold calibration for open-set plankton image recognition
May 15, 2026Xi Chen, Eryuan Huang, Yingjun Xiao +1Plankton Classifier Coral
School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China · School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, 510006, China · School of Environment, South China Normal University, Guangzhou, China +5
ICDAR 2026 Competition on Writer Identification and Pen Classification from Hand-Drawn Circles
May 8, 2026Thomas Gorges, Janne van der Loop, Lukas Hüttner +4Handwriting Biometrics
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany · Buchwissenschaft, Johannes Gutenberg-Universität Mainz, Germany
MolRecBench-Wild: A Real-World Benchmark for Optical Chemical Structure Recognition
May 7, 2026Haote Yang, Hui Wang, Chen Zhu +14Open-Set Recognition Mosaic
Shanghai Artificial Intelligence Laboratory · King’s College London · East China University of Science and Technology +5
Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentation
May 4, 2026Yao Lu, Rohit Mohan, Florian Drews +2Panoptic Segmentation Open-Vocabulary Object Detection
Department of Computer Science, University of Freiburg, Germany · Bosch Research, Robert Bosch GmbH, Germany
DMDSC: A Dynamic-Margin Deep Simplex Classifier for Open-Set Recognition on Medical Image Datasets
May 1, 2026Vishal, Arnav Aditya, Nitin Kumar +1Medical Imaging Datasets Imbalanced Classification
Shiv Nadar Institution of Eminence, Delhi NCR, India
Different Strokes for Different Folks: Writer Identification for Historical Arabic Manuscripts
Apr 24, 2026Hamza A. Abushahla, Ariel Justine N. Panopio, Layth Al-Khairulla +1Handwritten Text Recognition Authorship
Department of Computer Science and Engineering, American University of Sharjah, Sharjah 26666, United Arab Emirates
Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation
Apr 23, 2026Yingkai Yang, Chaoqi Chen, Hui HuangTest-Time Adaptation Domain Adaptation
College of Computer Science and Software Engineering, Shenzhen University
Energy-Based Open-Set Active Learning for Object Classification
Apr 22, 2026Zongyao Lyu, William J. BeksiPool-Based Active Learning Active Learning
The University of Texas at Arlington, Arlington TX 76019, USA
HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images
Apr 20, 2026Pourya Shamsolmoali, Masoumeh Zareapoor, Michael Felsberg +3Object Detection Aerial Imagery
Department of Computer Science, University of York, UK · SEIEE, Shanghai Jiao Tong University, China · Computer Vision Laboratory, Linkoping University, Sweden +2
iDocV2: Leveraging Self-Supervision and Open-Set Detection for Improving Pattern Spotting in Historical Documents
Apr 17, 2026Jose M. Saavedra, Crhistopher Stears, Marcelo Pizarro +2Open-Set Recognition Self-Supervised Learning
Facultad de Ingeniería y Ciencias Aplicadas, Universidad de los Andes, Chile, Av. Monseñor Álvaro del Portillo, 12455, Santiago, 7620086, RM, Chile.
Open-Set Vein Biometric Recognition with Deep Metric Learning
Apr 16, 2026Paweł Pilarek, Marcel Musiałek, Anna GórskaBiometrics Open-Set Recognition
Wroclaw University of Science and Technology, Wroclaw, Poland
MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration
Nov 20, 2022Zongyao Lyu, Nolan B. Gutierrez, William J. BeksiOpen-Set Recognition Modern Deep Networks
The University of Texas at Arlington Arlington, TX, USA

Oct 1, 2026, cs.CVJ/K move · Enter open · S save

SmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing

Thiru Thillai Nadarasar Bahavan, Yu Xia, Sachith Seneviratne, Saman Halgamuge

The University of Melbourne Parkville, VIC, Australia

Open-Set Recognition Smoothing Fine-Grained Perception Spherical Latent Space

Open paper AskPDF arXiv

Open Set Recognition (OSR) aims to enable models to accurately classify known classes while rejecting samples from unseen classes. A key challenge in OSR lies in the inability to model the unbounded distribution of unknown classes during training, often leading to the misclassification of samples from these classes. Rather than modeling unknowns, recent work shapes the feature space so that known classes are compact and well separated, and spherical representation learning methods have achieved strong results this way. Label smoothing has been identified as one of the key drivers of this success, yet it applies the same coefficient to every training sample, regardless of how well each sample is already embedded. We show that the spherical representation learning objectives used in OSR share a single alignment--uniformity structure in which labels enter only through the alignment term. Label smoothing therefore acts as an alignment dial, and a fixed coefficient sets this dial to the same value for every sample. We propose a plug-in, SmoothOperator (SmoothOP), which sets the smoothing coefficient of each sample from its \textbf{prominence}, an embedding-space signal measuring how clearly the sample's own class stands out against its strongest competing class. Our method integrates into four existing spherical representation learning methods at minimal training overhead. SmoothOP assigns strong smoothing to samples with high prominence, which reduces their alignment and relaxes their pull. On the Semantic Shift Benchmark, SmoothOP-augmented variants generally outperform their base objectives across datasets, degrees of semantic shift, and OSR post-processors, with gains of up to 4.7% in AUROC, OSCR, and closed-set accuracy.

Momentum

Related topics

Latest papers 40