用局部物体位置信息提升少样本图像分类准确率
Object-Centric Cropping for Visual Few-Shot Classification
- 基于物体局部位置信息增强分类性能
- 仅需指点一个像素点即可实现显著提升
- 适合低资源场景下的图像识别任务
在少样本图像分类中，每类仅有一个样本时，图像中的多物体或复杂背景会带来歧义，严重影响分类效果。本研究发现，引入物体在图像中的局部定位信息能显著提升分类性能。更重要的是，通过使用Segment Anything Model，只需指出目标物体的一个像素点，或采用完全无监督的前景提取方法，即可实现大部分性能提升。
原文摘要 · Abstract (English)
In the domain of Few-Shot Image Classification, operating with as little as one example per class, the presence of image ambiguities stemming from multiple objects or complex backgrounds can significantly deteriorate performance. Our research demonstrates that incorporating additional information about the local positioning of an object within its image markedly enhances classification across established benchmarks. More importantly, we show that a significant fraction of the improvement can be achieved through the use of the Segment Anything Model, requiring only a pixel of the object of interest to be pointed out, or by employing fully unsupervised foreground object extraction methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。