arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.11297cs.CV
收藏

使大型视觉语言模型成为优秀的少样本学习者

Making Large Vision Language Models to be Good Few-shot Learners

Hohai University(河海大学);HKUST(香港科技大学);Griffith University(格里菲斯大学)

Fan Liu, Wenwen Cai, Jian Huo, Chuanyi Zhang, Delong Chen, Jun Zhou

AI总结:

针对大型视觉语言模型在少样本分类中学习不足和定位偏差的问题,本文采用元学习策略,结合标签增强和候选选择,提升了模型在通用和细粒度数据集上的分类性能。

摘要:

少样本分类(FSC)是计算机视觉中一项基础但具有挑战性的任务,涉及从有限数据中识别新类别。尽管以往的方法侧重于增强视觉特征或整合额外模态,大型视觉语言模型(LVLMs)凭借其丰富的知识和强大的视觉感知能力,提供了一种有前景的替代方案。然而,在FSC任务中,LVLMs存在学习特定响应格式而非有效提取支持数据中有用信息的风险。在本文中,我们研究了LVLMs在FSC中的表现,并识别出关键问题,如学习不足和存在严重的定位偏差。为应对上述挑战,我们采用元学习策略来教导模型“学会学习”。通过构建丰富的元任务集进行指令微调,LVLMs增强了从少样本支持数据中提取信息以进行分类的能力。此外,我们通过标签增强和候选选择分别在微调和推理阶段进一步提升LVLMs的少样本学习能力。标签增强通过字符扰动策略实现,以确保模型专注于支持信息。候选选择利用属性描述来过滤不可靠的候选并简化任务。大量实验表明,我们的方法在通用和细粒度数据集上均取得了优越的性能。此外,我们的候选选择策略已被证明对免训练的LVLMs有益。

英文摘要:

Few-shot classification (FSC) is a fundamental yet challenging task in computer vision that involves recognizing novel classes from limited data. While previous methods have focused on enhancing visual features or incorporating additional modalities, Large Vision Language Models (LVLMs) offer a promising alternative due to their rich knowledge and strong visual perception. However, LVLMs risk learning specific response formats rather than effectively extracting useful information from support data in FSC tasks. In this paper, we investigate LVLMs' performance in FSC and identify key issues such as insufficient learning and the presence of severe positional biases. To tackle the above challenges, we adopt the meta-learning strategy to teach models "learn to learn". By constructing a rich set of meta-tasks for instruction fine-tuning, LVLMs enhance the ability to extract information from few-shot support data for classification. Additionally, we further boost LVLM's few-shot learning capabilities through label augmentation and candidate selection in the fine-tuning and inference stage, respectively. Label augmentation is implemented via a character perturbation strategy to ensure the model focuses on support information. Candidate selection leverages attribute descriptions to filter out unreliable candidates and simplify the task. Extensive experiments demonstrate that our approach achieves superior performance on both general and fine-grained datasets. Furthermore, our candidate selection strategy has been proven beneficial for training-free LVLMs.

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。

↑