按年被提到
20232023 · 1 次2026
视觉、语音与图像生成›视觉语言与自监督表征·arXiv:2311.06242 · cs.CV

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Bin Xiao, Haiping Wu, Weijian Xu, Xiyang Dai, Houdong Hu, Yumao Lu, Michael Zeng, Ce Liu, Lu Yuan · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-11-13 · 最近 2025-02-07
2不同的人
2活跃月份
2讨论串
337被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We introduce Florence-2, a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks. While existing large vision models excel in transfer learning, they struggle to perform a diversity of tasks with simple instructions, a capability that implies handling the complexity of various spatial hierarchy and semantic granularity. Florence-2 was designed to take text-prompt as task instructions and generate desirable results in text forms, whether it be captioning, object detection, grounding or segmentation. This multi-task learning setup demands large-scale, high-quality annotated data. To this end, we co-developed FLD-5B that consists of 5.4 billion comprehensive visual annotations on 126 million images, using an iterative strategy of automated image annotation and model refinement. We adopted a sequence-to-sequence structure to train Florence-2 to perform versatile and comprehensive vision tasks. Extensive evaluations on numerous tasks demonstrated Florence-2 to be a strong vision foundation model contender with unprecedented zero-shot and fine-tuning capabilities.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论coder543 · 2025-02

“I'm somewhat surprised neither this article nor the previous one mention anything about the Florence-2 model series. I had thought that Florence-2 was not just surprisingly capable for this kind of work, but also easily fine-tunable for a particular kind of document, when you expect to process a lot of instances of that document and want to further optimi…”

Why LLMs still have problems with OCR原评论 ↗
被提交为 story · 1 次