PulseAugur
实时 11:05:22
English(EN) A Coreset Selection Framework with Ensemble Aggregation for Image Classification

新框架优化图像分类训练数据选择

研究人员开发了一个新的图像分类框架,通过有效地选择代表性数据子集来解决在大数据集上训练的挑战。该框架称为 SCOre-Stratified Selection (SCOSS),根据分数和每个区间内的样本对数据进行分区,并结合多次运行的集成聚合。实验表明,SCOSS 与现有方法相比具有竞争力,对于 Simple Graph Convolution (SGC) 分类器尤其有效,并且在准确性和效率之间提供了有利的权衡,尤其是在使用较少标记样本时。 AI

影响 该框架可以提高在大型图像数据集上训练 AI 模型的效率,从而可能降低计算成本并加速开发。

排序理由 该集群包含一篇详细介绍图像分类新框架的学术论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新框架优化图像分类训练数据选择

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Pedro Rocha Dantas, Lucas Pascotti Valem ·

    用于图像分类的具有集成聚合的核心集选择框架

    arXiv:2607.09100v1 Announce Type: cross Abstract: The rapid growth of image data has produced large-scale datasets, raising concerns about the time and memory costs of model training. Selecting representative training subsets, however, remains challenging: individual sample contr…

  2. arXiv cs.AI TIER_1 English(EN) · Lucas Pascotti Valem ·

    用于图像分类的具有集成聚合的核心集选择框架

    The rapid growth of image data has produced large-scale datasets, raising concerns about the time and memory costs of model training. Selecting representative training subsets, however, remains challenging: individual sample contributions are unclear, and model behavior varies ac…