Open Vocabulary Object Detection On Mscoco

评估指标

AP 0.5

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
Cooperative Foundational Models	50.3	Enhancing Novel Object Detection via Cooperative Foundational Models
DE-ViT	50	Detect Everything with Few Examples
DITO	46.1	Region-centric Image-Language Pretraining for Open-Vocabulary Detection
OV-DQUO(RN50x4)	45.6	OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision
LP-OVOD (OWL-ViT Proposals)	44.9	LP-OVOD: Open-Vocabulary Object Detection by Linear Probing
CLIPSelf	44.3	CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
CORA+	43.1	CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching
BARON	42.7	Aligning Bag of Regions for Open-Vocabulary Object Detection
SIA-OVD (RN50x4)	41.9	SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection
CORA	41.7	CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching
RALF	41.3	Retrieval-Augmented Open-Vocabulary Object Detection
LP-OVOD	40.5	LP-OVOD: Open-Vocabulary Object Detection by Linear Probing
Region-CLIP (RN50x4-C4)	39.3	RegionCLIP: Region-based Language-Image Pretraining
OV-DQUO(R50)	39.2	OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision
Object-Centric-OVD	36.9	Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection
CLIM (RN50)	36.9	CLIM: Contrastive Language-Image Mosaic for Region Representation
OADP (G-OVD)	35.6	Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection
SIA-OVD (RN50)	35.5	SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection
VL-PLM (RN50)	34.4	Exploiting Unlabeled Data with Vision and Language Models for Object Detection
CFM-ViT	34.1	Contrastive Feature Masking Open-Vocabulary Vision Transformer	-

0 of 30 row(s) selected.