arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.03073cs.CVcs.RO
收藏

Proto-CLIP: 面向少样本学习的视觉语言原型网络

Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning

University of Texas at Dallas(德克萨斯大学达拉斯分校);NVIDIA(英伟达)

Jishnu Jaykumar P, Kamalesh Palanisamy, Yu-Wei Chao, Xinya Du, Yu Xiang

AI总结:

本研究提出基于CLIP的少样本学习框架Proto-CLIP,联合适配图像与文本编码器嵌入并对齐对应类别的双模态原型,兼具免训练和微调版本,在基准数据集及机器人感知场景中验证了有效性。

摘要:

我们提出了一种利用CLIP等大规模视觉语言模型的新型少样本学习框架。受单模态少样本学习原型网络的启发,我们提出了Proto-CLIP,该模型利用图像原型和文本原型进行少样本学习。具体而言,Proto-CLIP使用少样本样本以联合方式适配来自CLIP的图像与文本编码器嵌入。两个编码器输出的嵌入被用于计算各图像类别的对应原型以进行分类。在适配过程中,我们提出对齐对应类别的图像原型和文本原型。由于两类原型的贡献得到强化,这种对齐对少样本分类十分有益。Proto-CLIP同时具备免训练和微调两种变体。我们通过在少样本学习基准数据集以及真实世界机器人感知场景下开展实验,验证了该方法的有效性。项目页面地址为:https://irvlutd.github.io/Proto-CLIP

英文摘要:

We propose a novel framework for few-shot learning by leveraging large-scale vision-language models such as CLIP. Motivated by unimodal prototypical networks for few-shot learning, we introduce Proto-CLIP which utilizes image prototypes and text prototypes for few-shot learning. Specifically, Proto-CLIP adapts the image and text encoder embeddings from CLIP in a joint fashion using few-shot examples. The embeddings from the two encoders are used to compute the respective prototypes of image classes for classification. During adaptation, we propose aligning the image and text prototypes of the corresponding classes. Such alignment is beneficial for few-shot classification due to the reinforced contributions from both types of prototypes. Proto-CLIP has both training-free and fine-tuned variants. We demonstrate the effectiveness of our method by conducting experiments on benchmark datasets for few-shot learning, as well as in the real world for robot perception. The project page is available at https://irvlutd.github.io/Proto-CLIP

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。

↑