Papers Region Proposal
“Region Proposal” 태그가 달린 논문 373편 · 필터 해제
Bridging Annotation Gaps: Transferring Labels to Align Object Detection Datasets
Combining multiple object detection datasets offers a path to improved generalisation but is hindered by inconsistencies in class semantics and bounding box annotations. Some methods to address this assume shared label t…
object-detectionObject DetectionRegion ProposalGeneralization-Enhanced Few-Shot Object Detection in Remote Sensing
Remote sensing object detection is particularly challenging due to the high resolution, multi-scale features, and diverse ground object characteristics inherent in satellite and UAV imagery. These challenges necessitate …
Few-Shot LearningFew-Shot Object DetectionObjectobject-detection+2OralXrays-9: Towards Hospital-Scale Panoramic X-ray Anomaly Detection via Personalized Multi-Object Query-Aware Mining
In clinical practice, panoramic dental radiography is a widely employed imaging technique that can provide a detailed and comprehensive view of dental structures and surrounding tissues for identifying various oral a…
Anomaly DetectionDiagnosticRegion ProposalOnline Pseudo-Label Unified Object Detection for Multiple Datasets Training
The Unified Object Detection (UOD) task aims to achieve object detection of all merged categories through training on multiple datasets, and is of great significance in comprehensive object detection scenarios. In this p…
Objectobject-detectionObject DetectionPseudo Label+2Diffusion-Based Depth Inpainting for Transparent and Reflective Objects
Transparent and reflective objects, which are common in our everyday lives, present a significant challenge to 3D imaging techniques due to their unique visual and optical properties. Faced with these types of objects, R…
Region ProposalTowards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis
Object detection models, widely used in security-critical applications, are vulnerable to backdoor attacks that cause targeted misclassifications when triggered by specific patterns. Existing backdoor defense techniques,…
backdoor defenseObjectobject-detectionObject Detection+2Lidar Panoptic Segmentation in an Open World
Addressing Lidar Panoptic Segmentation (LPS ) is crucial for safe deployment of autonomous vehicles. LPS aims to recognize and segment lidar points w.r.t. a pre-defined vocabulary of semantic classes, including thing cla…
Autonomous VehiclesInstance SegmentationPanoptic SegmentationPoint Cloud Segmentation+2ProteinRPN: Towards Accurate Protein Function Prediction with Graph-Based Region Proposals
Protein function prediction is a crucial task in bioinformatics, with significant implications for understanding biological processes and disease mechanisms. While the relationship between sequence and function has been …
Protein Function PredictionRegion ProposalVFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models
Existing vehicle detectors are usually obtained by training a typical detector (e.g., YOLO, RCNN, DETR series) on vehicle images based on a pre-trained backbone (e.g., ResNet, ViT). Some researchers also exploit and enha…
Contrastive LearningLanguage ModellingLarge Language ModelRegion Proposal+1Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation
Source-Free domain adaptive Object Detection (SFOD) is a promising strategy for deploying trained detectors to new, unlabeled domains without accessing source data, addressing significant concerns around data privacy and…
object-detectionObject DetectionPseudo LabelRegion Proposal+1Adaptive Modality Balanced Online Knowledge Distillation for Brain-Eye-Computer based Dim Object Detection
Advanced cognition can be extracted from the human brain using brain-computer interfaces. Integrating these interfaces with computer vision techniques, which possess efficient feature extraction capabilities, can achieve…
EEGElectroencephalogram (EEG)ERPKnowledge Distillation+3Semantic Enhanced Few-shot Object Detection
Few-shot object detection~(FSOD), which aims to detect novel objects with limited annotated instances, has made significant progress in recent years. However, existing methods still suffer from biased representations, es…
Few-Shot Object DetectionObjectobject-detectionObject Detection+3Versatile Teacher: A Class-aware Teacher-student Framework for Cross-domain Adaptation
Addressing the challenge of domain shift between datasets is vital in maintaining model performance. In the context of cross-domain object detection, the teacher-student framework, a widely-used semi-supervised model, ha…
Domain Adaptationobject-detectionObject DetectionPseudo Label+1A Realistic Protocol for Evaluation of Weakly Supervised Object Localization
Weakly Supervised Object Localization (WSOL) allows training deep learning models for classification and localization (LOC) using only global class-level labels. The absence of bounding box (bbox) supervision during trai…
Model SelectionObjectObject LocalizationRegion Proposal+1Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregation
Open-vocabulary object detection (OVOD) aims at localizing and recognizing visual objects from novel classes unseen at the training time. Whereas, empirical studies reveal that advanced detectors generally assign lower s…
Objectobject-detectionObject DetectionOpen-vocabulary object detection+2Generative Region-Language Pretraining for Open-Ended Object Detection
In recent research, significant attention has been devoted to the open-vocabulary object detection task, aiming to generalize beyond the limited number of classes labeled during training and detect objects described by a…
Language ModelingLanguage ModellingObjectobject-detection+4Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery
The goal of this paper is to perform object detection in satellite imagery with only a few examples, thus enabling users to specify any object class with minimal annotation. To this end, we explore recent methods and ide…
Few-Shot Object DetectionObjectobject-detectionObject Detection+1Debiased Novel Category Discovering and Localization
In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects …
Contrastive LearningNovel Class DiscoveryObjectobject-detection+2CPN: Complementary Proposal Network for Unconstrained Text Detection
Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based. While Segmentation-based methods are well-suited for irregular shapes, they struggle with compact or overl…
Region ProposalScene Text DetectionText DetectionWeakly Supervised Open-Vocabulary Object Detection
Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories within a single training dataset. In this pap…
AttributeNovel ConceptsObjectobject-detection+6