Open Vocabulary Object Detection On Lvis V1 0

评估指标

AP novel-LVIS base training

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
LaMI-DETR	43.4	LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction
DITO	40.4	Region-centric Image-Language Pretraining for Open-Vocabulary Detection
OV-DQUO(ViT-L/14)	39.3	OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision
CoDet (EVA02-L)	37.0	CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
CLIPSelf	34.9	CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
OVMR	34.4	OVMR: Open-Vocabulary Recognition with Multi-Modal References
DE-ViT	34.3	Detect Everything with Few Examples
CFM-ViT	33.9	Contrastive Feature Masking Open-Vocabulary Vision Transformer	-
CLIM (RN50x64)	32.3	CLIM: Contrastive Language-Image Mosaic for Region Representation
RO-ViT	32.1	Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
Prova (Swin-Base)	31.5	Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection
RTGen	30.2	RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection
OV-DQUO(ViT-B/16)	29.7	OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision
ViLD-ensemble w/ ALIGN (Eb7-FPN)	26.3	Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
OWL-ViT (CLIP-L/14)	25.6	Simple Open-Vocabulary Object Detection with Vision Transformers
POMP	25.2	Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition
BARON	22.6	Aligning Bag of Regions for Open-Vocabulary Object Detection
MEDet	22.4	Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization
Region-CLIP (RN50x4-C4)	22.0	RegionCLIP: Region-based Language-Image Pretraining
RALF	21.9	Retrieval-Augmented Open-Vocabulary Object Detection

0 of 28 row(s) selected.