Open Vocabulary Object Detection On Lvis V1 0

Métriques

AP novel-LVIS base training

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	AP novel-LVIS base training	Paper Title	Repository
LaMI-DETR	43.4	LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction
RO-ViT	32.1	Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
OADP	21.7	Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection
X-Paste	21.4	X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
Detic	17.8	Detecting Twenty-thousand Classes using Image-level Supervision
OVMR	34.4	OVMR: Open-Vocabulary Recognition with Multi-Modal References
POMP	25.2	Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition
OWL-ViT (CLIP-L/14)	25.6	Simple Open-Vocabulary Object Detection with Vision Transformers
Region-CLIP (RN50-C4)	17.1	RegionCLIP: Region-based Language-Image Pretraining
Object-Centric-OVD	21.1	Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection
ViLD (R50-FPN)	16.1	Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
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	-
DITO	40.4	Region-centric Image-Language Pretraining for Open-Vocabulary Detection	-
CLIM (RN50x64)	32.3	CLIM: Contrastive Language-Image Mosaic for Region Representation
ViLD-ensemble (R50-FPN)	16.6	Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
OV-DQUO(ViT-L/14)	39.3	OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision
ViLD-ensemble (R152-FPN)	18.7	Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
MEDet	22.4	Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization
OV-DQUO(ViT-B/16)	29.7	OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision

0 of 28 row(s) selected.