RefCOCOg
Progress Over Time
Interactive timeline showing model performance evolution on RefCOCOg
RefCOCOg Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Amazon | — | — | — |
What is RefCOCOg?
RefCOCOg is a referring expression comprehension benchmark that evaluates spatial grounding in images. Given a natural language expression describing an object, the model must localize the correct region, evaluated by accuracy at a 0.5 IoU threshold. It features longer, more descriptive expressions than RefCOCO and RefCOCO+.
RefCOCOg is a multimodal benchmark evaluating models on multimodal, grounding, and vision tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.9, with the leader at 0.9.
Compare leaders on the best AI for multimodal, best AI for grounding and best AI for vision leaderboards.
Current leaders
Nova 2 Omni from Amazon currently leads the RefCOCOg leaderboard with a score of 0.863 across 1 evaluated AI models.
Source paper
- Title
- Generation and Comprehension of Unambiguous Object Descriptions
- Authors
- Junhua Mao, Jonathan Huang, Alexander Toshev, Oana Camburu, and 2 others
- Published
- arXiv
- 1511.02283
Abstract
We propose a method that can generate an unambiguous description (known as a referring expression) of a specific object or region in an image, and which can also comprehend or interpret such an expression to infer which object is being described. We show that our method outperforms previous methods that generate descriptions of objects without taking into account other potentially ambiguous objects in the scene. Our model is inspired by recent successes of deep learning methods for image captioning, but while image captioning is difficult to evaluate, our task allows for easy objective evaluation. We also present a new large-scale dataset for referring expressions, based on MS-COCO. We have released the dataset and a toolbox for visualization and evaluation, see https://github.com/mjhucla/Google_Refexp_toolbox
FAQ
Common questions about the RefCOCOg benchmark and leaderboard.