Papers Open Set Learning
“Open Set Learning” 태그가 달린 논문 267편 · 필터 해제
ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment
We address the task of zero-shot fine-grained video classification, where no video examples or temporal annotations are available for unseen action classes. While contrastive vision-language models such as SigLIP demonst…
Dynamic Time WarpingLarge Language ModelOpen Set Learningtext similarity+2Disentangled representations of microscopy images
Microscopy image analysis is fundamental for different applications, from diagnosis to synthetic engineering and environmental monitoring. Modern acquisition systems have granted the possibility to acquire an escalating …
ClassificationDisentanglementimage-classificationImage Classification+2SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
Recent advancements in deep learning have greatly enhanced 3D object recognition, but most models are limited to closed-set scenarios, unable to handle unknown samples in real-world applications. Open-set recognition (OS…
3D Object RecognitionObject RecognitionOpen Set LearningHyperbolic Dual Feature Augmentation for Open-Environment
Feature augmentation generates novel samples in the feature space, providing an effective way to enhance the generalization ability of learning algorithms with hyperbolic geometry. Most hyperbolic feature augmentation is…
class-incremental learningClass Incremental LearningFew-Shot Learningimage-classification+5Open-Set Semi-Supervised Learning for Long-Tailed Medical Datasets
Many practical medical imaging scenarios include categories that are under-represented but still crucial. The relevance of image recognition models to real-world applications lies in their ability to generalize to these …
Open Set LearningStructure-based Anomaly Detection and Clustering
Anomaly detection is a fundamental problem in domains such as healthcare, manufacturing, and cybersecurity. This thesis proposes new unsupervised methods for anomaly detection in both structured and streaming data settin…
Anomaly DetectionClusteringMalware ClassificationOpen Set LearningMalware families discovery via Open-Set Recognition on Android manifest permissions
Malware are malicious programs that are grouped into families based on their penetration technique, source code, and other characteristics. Classifying malware programs into their respective families is essential for bui…
Malware ClassificationMalware DetectionOpen Set LearningInformed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation
Open set recognition (OSR) is devised to address the problem of detecting novel classes during model inference. Even in recent vision models, this remains an open issue which is receiving increasing attention. Thereby, a…
Data AugmentationOpen Set LearningOut-of-Distribution DetectionSelf-Supervised LearningSynthetic Non-stationary Data Streams for Recognition of the Unknown
The problem of data non-stationarity is commonly addressed in data stream processing. In a dynamic environment, methods should continuously be ready to analyze time-varying data -- hence, they should enable incremental t…
Open Set LearningBackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priors
Open set recognition (OSR) requires models to classify known samples while detecting unknown samples for real-world applications. Existing studies show impressive progress using unknown samples from auxiliary datasets to…
Open Set LearningOpen-Set Plankton Recognition
This paper considers open-set recognition (OSR) of plankton images. Plankton include a diverse range of microscopic aquatic organisms that have an important role in marine ecosystems as primary producers and as a base of…
image-classificationImage ClassificationOpen Set LearningSphOR: A Representation Learning Perspective on Open-set Recognition for Identifying Unknown Classes in Deep Learning Models
The widespread use of deep learning classifiers necessitates Open-set recognition (OSR), which enables the identification of input data not only from classes known during training but also from unknown classes that might…
Open Set LearningRepresentation LearningOpen-Set Recognition of Novel Species in Biodiversity Monitoring
Machine learning is increasingly being applied to facilitate long-term, large-scale biodiversity monitoring. With most species on Earth still undiscovered or poorly documented, species-recognition models are expected to …
Fine-Grained Image RecognitionOpen Set LearningOut-of-Distribution DetectionG-OSR: A Comprehensive Benchmark for Graph Open-Set Recognition
Graph Neural Networks (GNNs) have achieved significant success in machine learning, with wide applications in social networks, bioinformatics, knowledge graphs, and other fields. Most research assumes ideal closed-set en…
Anomaly DetectionGraph Anomaly DetectionGraph LearningKnowledge Graphs+2A Survey of Text Classification Under Class Distribution Shift
The basic underlying assumption of machine learning (ML) models is that the training and test data are sampled from the same distribution. However, in daily practice, this assumption is often broken, i.e.~the distributio…
ArticlesContinual LearningOpen Set LearningSurvey+3Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data
We present RASO, a foundation model designed to Recognize Any Surgical Object, offering robust open-set recognition capabilities across a broad range of surgical procedures and object classes, in both surgical images and…
Action RecognitionOpen Set LearningTAGWeakly-supervised LearningCross-Rejective Open-Set SAR Image Registration
Synthetic Aperture Radar (SAR) image registration is an essential upstream task in geoscience applications, in which pre-detected keypoints from two images are employed as observed objects to seek matched-point pairs…
Image RegistrationOpen Set LearningMitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
Open-Set Domain Generalization (OSDG) is a challenging task requiring models to accurately predict familiar categories while minimizing confidence for unknown categories to effectively reject them in unseen domains. Whil…
DenoisingDomain GeneralizationMeta-LearningModel Optimization+1Robustness-enhanced Myoelectric Control with GAN-based Open-set Recognition
Electromyography (EMG) signals are widely used in human motion recognition and medical rehabilitation, yet their variability and susceptibility to noise significantly limit the reliability of myoelectric control systems.…
Electromyography (EMG)Open Set LearningCOOOL: Challenge Of Out-Of-Label A Novel Benchmark for Autonomous Driving
As the Computer Vision community rapidly develops and advances algorithms for autonomous driving systems, the goal of safer and more efficient autonomous transportation is becoming increasingly achievable. However, it is…
Anomaly DetectionAutonomous DrivingDomain AdaptationOpen Set Learning+1