English(EN) Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domains

新的MIV-head方法可在骨干网络冻结的情况下实现少样本分类

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员开发了一种名为“MIV-head”的新方法，用于少样本分类任务，尤其是在特征提取器（骨干网络）无法进行微调时非常有效。该方法将分类视为一系列多实例验证任务，利用冻结骨干网络的静态嵌入。在Meta-Dataset基准上的实验表明，MIV-head在实现与最先进的适配器方法相当的准确率的同时，显著降低了适应成本。 AI

影响该方法可以在模型微调受限的情况下，实现更高效的少样本学习。

排序理由该集群包含一篇详细介绍少样本分类新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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

本文如何被排名

Signal score: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍少样本分类新方法的论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Xin Xu, Eibe Frank, Geoffrey Holmes · 2026-10-23 04:00

Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domains

arXiv:2507.00401v2 Announce Type: replace-cross Abstract: We investigate cross-domain few-shot learning under the constraint that fine-tuning of backbones (i.e., feature extractors) is impossible or infeasible---a scenario that is increasingly common in practical use cases---and …

本文如何被排名

报道来源 [1]

Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domains

相关实体

相关话题