Open World Object Detection
7개 벤치마크 · 논문 55편 · 이 태스크의 논문 보기 →
Benchmarks
COCO 2017 (Sports, Food)
COCO VOC to non-VOC
PASCAL VOC 2007
COCO-Mix
COCO-OOD
Most implemented
Learning Open-World Object Proposals without Learning to Classify
Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection
OW-DETR: Open-world Detection Transformer
Towards Open World Object Detection
OW-OVD: Unified Open World and Open Vocabulary Object Detection
YOLO-UniOW: Efficient Universal Open-World Object Detection
Papers
CODE: Cross-Modal Calibration and Dynamic Suppression for Open World Object Detection
Open World Object Detection (OWOD) built on multimodal foundation models often suffers from semantic ambiguity caused by unidirectional text-to-vision matching, while rigid outlier penalties may over-suppress unknown obj…
Open World Object DetectionREAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling
Open-World Object Detection (OWOD) requires detectors to identify previously unseen objects as unknown and incrementally incorporate them into the set of known categories, while preserving previously acquired knowledge. …
Open World Object DetectionDetecting Unknown Objects via Energy-based Separation for Open World Object Detection
In this work, we tackle the problem of Open World Object Detection (OWOD). This challenging scenario requires the detector to incrementally learn to classify known objects without forgetting while identifying unknown obj…
Open World Object DetectionImplicit Non-Causal Factors are Out via Dataset Splitting for Domain Generalization Object Detection
Open world object detection faces a significant challenge in domain-invariant representation, i.e., implicit non-causal factors. Most domain generalization (DG) methods based on domain adversarial learning (DAL) pay much…
Open World Object DetectionDomain GeneralizationData AugmentationTowards Open World Detection: A Survey
For decades, Computer Vision has aimed at enabling machines to perceive the external world. Initial limitations led to the development of highly specialized niches. As success in each task accrued and research progressed…
Open World Object DetectionSaliency DetectionDecoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection
Open World Object Detection (OWOD) is a challenging computer vision task that extends standard object detection by (1) detecting and classifying unknown objects without supervision, and (2) incrementally learning new obj…
object-detectionObject DetectionOpen World Object Detection