研究人员推出了一种名为 FlexiGrad 的新型无参数方法，旨在改进分层细粒度分类任务。该技术解决了由于应用于共享模型骨干的粗粒度和细粒度分类器产生的冲突梯度而导致的训练不稳定问题。通过选择性地去除有害的梯度分量并加强共享方向，FlexiGrad 实现了更稳定的优化，并能更好地保留全局结构和细粒度细节。该方法在 CUB-200-2011、FGVC-Aircraft 和 Stanford Cars 等基准数据集上展示了更高的准确性，并能无缝集成到现有架构中。 AI
影响 通过稳定训练和提高分层数据集的准确性来增强细粒度图像分类。
排序理由 该集群描述了一篇详细介绍分类任务新方法的最新研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Many fine-grained recognition tasks contain hierarchical labels such as order, family and species. Although this supervision should be beneficial, jointly optimising all levels often leads to unstable training because coarse and fine classifiers impose inconsistent gradients on t…
arXiv:2607.17563v1 Announce Type: new Abstract: Many fine-grained recognition tasks contain hierarchical labels such as order, family and species. Although this supervision should be beneficial, jointly optimising all levels often leads to unstable training because coarse and fin…