General Object Foundation Model for Images and Videos at Scale

TL;DR

GLEE is a versatile, large-scale object foundation model for images and videos that unifies detection, segmentation, tracking, and identification, excelling in zero-shot transfer and multi-modal tasks.

Contribution

This work introduces GLEE, a unified multi-task object model trained on diverse data, enabling zero-shot generalization and integration with large language models.

Findings

Achieves state-of-the-art zero-shot performance on multiple benchmarks.

Handles diverse object perception tasks simultaneously.

Demonstrates strong generalization with over five million images.

Abstract

We present GLEE in this work, an object-level foundation model for locating and identifying objects in images and videos. Through a unified framework, GLEE accomplishes detection, segmentation, tracking, grounding, and identification of arbitrary objects in the open world scenario for various object perception tasks. Adopting a cohesive learning strategy, GLEE acquires knowledge from diverse data sources with varying supervision levels to formulate general object representations, excelling in zero-shot transfer to new data and tasks. Specifically, we employ an image encoder, text encoder, and visual prompter to handle multi-modal inputs, enabling to simultaneously solve various object-centric downstream tasks while maintaining state-of-the-art performance. Demonstrated through extensive training on over five million images from diverse benchmarks, GLEE exhibits remarkable versatility and improved generalization performance, efficiently tackling downstream tasks without the need for task-specific adaptation. By integrating large volumes of automatically labeled data, we further enhance its zero-shot generalization capabilities. Additionally, GLEE is capable of being integrated into Large Language Models, serving as a foundational model to provide universal object-level information for multi-modal tasks. We hope that the versatility and universality of our method will mark a significant step in the development of efficient visual foundation models for AGI systems. The model and code will be released at https://glee-vision.github.io .