Recognize Anything:一种强大的图像标注模型
Recognize Anything: A Strong Image Tagging Model
AI总结:
本研究提出图像标注基础模型RAM,采用基于大规模图文对的无人工标注新范式,经四步训练流程,在多个基准上零样本性能超越CLIP、BLIP及全监督方法,对标Google标注API,已开源以推动CV大模型发展。
摘要:
我们提出了Recognize Anything Model(RAM,识别万物模型):一种强大的图像标注基础模型。RAM为计算机视觉领域的大模型迈出了重要一步,展现出以高准确率识别任意常见类别的零样本能力。RAM引入了一种全新的图像标注范式,利用大规模图文对而非人工标注进行训练。\n RAM的开发包含四个关键步骤。首先,通过自动文本语义解析,大规模获取无需人工标注的图像标签。随后,通过统一图像描述和标注任务训练一个初步模型,分别以原始文本和解析得到的标签作为监督信号。第三步,采用数据引擎生成额外标注并清理错误标注。最后,使用处理后的数据重新训练模型,并借助一个规模更小但质量更高的数据集进行微调。\n 我们在众多基准上评估了RAM的标注能力,观察到其令人惊艳的零样本性能,显著优于CLIP和BLIP。值得注意的是,RAM甚至超过了全监督方法,且性能与Google标注API相当。我们已在https://recognize-anything.github.io/ 发布RAM,以推动计算机视觉大模型的发展。
英文摘要:
We present the Recognize Anything Model (RAM): a strong foundation model for image tagging. RAM makes a substantial step for large models in computer vision, demonstrating the zero-shot ability to recognize any common category with high accuracy. RAM introduces a new paradigm for image tagging, leveraging large-scale image-text pairs for training instead of manual annotations. The development of RAM comprises four key steps. Firstly, annotation-free image tags are obtained at scale through automatic text semantic parsing. Subsequently, a preliminary model is trained for automatic annotation by unifying the caption and tagging tasks, supervised by the original texts and parsed tags, respectively. Thirdly, a data engine is employed to generate additional annotations and clean incorrect ones. Lastly, the model is retrained with the processed data and fine-tuned using a smaller but higher-quality dataset. We evaluate the tagging capabilities of RAM on numerous benchmarks and observe impressive zero-shot performance, significantly outperforming CLIP and BLIP. Remarkably, RAM even surpasses the fully supervised manners and exhibits competitive performance with the Google tagging API. We are releasing the RAM at \url{https://recognize-anything.github.io/} to foster the advancements of large models in computer vision.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。