PulseAugur
中
实时 08:53:21
English(EN) Large Pretraining Datasets Don't Guarantee Robustness after Fine-Tuning in Image Classification

大型预训练数据集可能阻碍微调后的鲁棒性

作者 PulseAugur 编辑部 · [1 个来源] ·

一篇题为“大型预训练数据集不保证图像分类微调后的鲁棒性”的新研究论文指出，在海量数据集上预训练的模型进行微调可能导致严重的灾难性遗忘和分布外泛化能力的损失。研究人员提出了鲁棒性继承基准（ImageNet-RIB）来评估这种现象。他们的发现表明，在LAION-2B等更大、更多样化的数据集上预训练的模型可能比在较小数据集上训练的模型遭受更大的鲁棒性损失，这挑战了更大预训练总是带来更好下游性能的假设。 AI

影响 表明预训练数据的规模可能不会直接转化为微调后更好的鲁棒性，这可能会影响模型开发策略。

排序理由 分析模型鲁棒性的研究论文 [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

大型预训练数据集可能阻碍微调后的鲁棒性

本文如何被排名

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
分析模型鲁棒性的研究论文 [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Jaedong Hwang, Brian Cheung, Zhang-Wei Hong, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete ·

    大型预训练数据集不能保证图像分类微调后的鲁棒性

    arXiv:2410.21582v4 Announce Type: replace-cross Abstract: Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of maintaining the general performance of the model while allowing it to gain new skills. …

相关话题