 R-Bench
 R-Bench 
 Relationship validation dataset
 A repository providing preprocessed data and tools for evaluating and analyzing relationship hallucinations in large vision-language models.
[ICML2024] Repo for the paper `Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models'
20 stars
 2 watching
 1 forks
 
Language: Python 
last commit: about 1 year ago  Related projects:
| Repository | Description | Stars | 
|---|---|---|
|  | This repository provides a framework for visual relationship detection using deep learning models and pre-processing tools. | 94 | 
|  | Detects relationships and predicts predicates in images using language priors | 214 | 
|  | Analyzing and mitigating object hallucination in large vision-language models to improve their accuracy and reliability. | 136 | 
|  | Tools for creating reproducible research projects in R using Quarto and version control. | 680 | 
|  | This project presents a deep neural network architecture designed to detect visual relationships in images. | 202 | 
|  | This repository provides code and tools for training and evaluating models of referring relationships in computer vision | 260 | 
|  | An image-context reasoning benchmark designed to challenge large vision-language models and help improve their accuracy | 259 | 
|  | A library for exploring and validating machine learning data in TensorFlow | 766 | 
|  | Provides access to complex systems datasets from the Index of Complex Networks (ICON) database. | 7 | 
|  | Evaluates the capabilities of large multimodal models using a set of diverse tasks and metrics | 274 | 
|  | A C library that provides an R interface to PostgreSQL | 64 | 
|  | A validation library designed to simplify the use of Derby JS in JavaScript applications. | 1 | 
|  | Provides a toolbox for loading, visualizing, and evaluating a dataset of images with human annotations, including depth layers and age group classification. | 140 | 
|  | A collection of data for evaluating Chinese machine reading comprehension systems | 419 | 
|  | A collection of tools and guidelines for building responsible machine learning models | 682 |