GLEE/assets/MODEL_ZOO.md

GLEE MODEL ZOO

Introduction

GLEE maintains state-of-the-art (SOTA) performance across multiple tasks while preserving versatility and openness, demonstrating strong generalization capabilities. Here, we provide the model weights for all three stages of GLEE: '-pretrain', '-joint', and '-scaleup'. The '-pretrain' weights refer to those pretrained on Objects365 and OpenImages, yielding effective initializations from over three million detection data. The '-joint' weights are derived from joint training on 15 datasets, where the model achieves optimal performance. The '-scaleup' weights are obtained by incorporating additional automatically annotated SA1B and GRIT data, which enhance zero-shot performance and support a richer semantic understanding. Additionally, we offer weights fine-tuned on VOS data for interactive video tracking applications.

Stage 1: Pretraining

Name	Config	Weight
GLEE-Lite-pretrain	Stage1_pretrain_openimage_obj365_CLIPfrozen_R50.yaml	Model
GLEE-Plus-pretrain	Stage1_pretrain_openimage_obj365_CLIPfrozen_SwinL.yaml	Model
GLEE-Pro-pretrain	Stage1_pretrain_openimage_obj365_CLIPfrozen_EVA02L_LSJ1536.yaml	Model

Stage 2: Image-level Joint Training

Name	Config	Weight
GLEE-Lite-joint	Stage2_joint_training_CLIPteacher_R50.yaml	Model
GLEE-Plus-joint	Stage2_joint_training_CLIPteacher_SwinL	Model
GLEE-Pro-joint	Stage2_joint_training_CLIPteacher_EVA02L.yaml	Model

Stage 3: Scale-up Training

Name	Config	Weight
GLEE-Lite-scaleup	Stage3_scaleup_CLIPteacher_R50.yaml	Model
GLEE-Plus-scaleup	Stage3_scaleup_CLIPteacher_SwinL	Model
GLEE-Pro-scaleup	Stage3_scaleup_CLIPteacher_EVA02L.yaml	Model

Single Tasks

We also provide models trained on a VOS task with ResNet-50 backbone:

Name	Config	Weight
GLEE-Lite-vos	VOS_joint_finetune_R50.yaml	Model