用层次语义关联提升细粒度分类，无需标注或裁剪。
EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification Task
- 构建多粒度分支网络，利用分类层级关系作为监督信号。
- 在CIFAR-100、CUB-200-2011和FGVC-Aircraft上达到先进性能。
- 无需人工标注或裁剪，适合无标注数据的细粒度识别场景。
细粒度分类模型旨在关注区分高度相似类别所需的细节，尤其当类内差异大而类间差异小时。现有方法多依赖部位标注（如边界框、部位位置或文本属性）或复杂技术自动提取注意力图。我们指出，基于部位的方法（包括自动裁剪）存在局部特征表征不完整的问题，而细粒度分类应识别层次结构中的“叶子”节点，人类则通过形成语义关联进行识别。本文提出端到端深度神经网络EnGraf-Net，将分类层次结构（分类学）作为语义关联的监督信号。在三个知名数据集CIFAR-100、CUB-200-2011和FGVC-Aircraft上的大量实验表明，EnGraf-Net优于许多现有细粒度模型，性能媲美最新最先进方法，且无需裁剪或人工标注。
原文摘要 · Abstract (English)
Fine-grained classification models are designed to focus on the relevant details necessary to distinguish highly similar classes, particularly when intra-class variance is high and inter-class variance is low. Most existing models rely on part annotations such as bounding boxes, part locations, or textual attributes to enhance classification performance, while others employ sophisticated techniques to automatically extract attention maps. We posit that part-based approaches, including automatic cropping methods, suffer from an incomplete representation of local features, which are fundamental for distinguishing similar objects. While fine-grained classification aims to recognize the leaves of a hierarchical structure, humans recognize objects by also forming semantic associations. In this paper, we leverage semantic associations structured as a hierarchy (taxonomy) as supervised signals within an end-to-end deep neural network model, termed EnGraf-Net. Extensive experiments on three well-known datasets CIFAR-100, CUB-200-2011, and FGVC-Aircraft demonstrate the superiority of EnGraf-Net over many existing fine-grained models, showing competitive performance with the most recent state-of-the-art approaches, without requiring cropping techniques or manual annotations.
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。