按年被提到
20222022 · 2 次2026
视觉、语音与图像生成›视觉语言与自监督表征·arXiv:2205.06230 · cs.CV

Simple Open-Vocabulary Object Detection with Vision Transformers

Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai 等 14 人 · 2022
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2022-08-06 · 最近 2022-10-02
2不同的人
2活跃月份
2讨论串
119被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and open-vocabulary setting, where training data is relatively scarce. In this paper, we propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. Our analysis of the scaling properties of this setup shows that increasing image-level pre-training and model size yield consistent improvements on the downstream detection task. We provide the adaptation strategies and regularizations needed to attain very strong performance on zero-shot text-conditioned and one-shot image-conditioned object detection. Code and models are available on GitHub.

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bertdb · 2022-10

“Hello HN! We've built an interactive demo of Google AI's OWL-ViT [1] zero-shot object detection model, using Hugging Face transformers. Regular object detection models are trained on a fixed set of categories, for example cats, dogs and birds. If you want to detect a new type of object, like a horse, you have to collect and label images with horses and …”

Show HN: Zero-shot object detection demo原评论 ↗
被提交为 story · 1 次