English(EN) Correlates of Image Memorability in Vision Encoders: Activations, Attention Entropy, Patch Uniformity and Autoencoder Losses

研究人员探索视觉编码器中的图像可记忆性相关性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-05 04:00

研究人员调查了视觉编码器中与人类图像可记忆性相关的因素。他们分析了激活、注意力熵和块均匀性，发现这些特征具有一定的预测能力。一种使用视觉编码器表示上的稀疏自动编码器损失的新方法，其表现优于先前的方法，表明重建损失是图像可记忆性的有力指标。 AI

影响为了解视觉模型如何处理和保留信息提供了见解，可能指导未来模型开发以增强记忆或识别能力。

排序理由学术论文发表在arXiv上，详细介绍了视觉编码器中图像可记忆性相关性的新发现。[lever_c_demoted from research: ic=1 ai=1.0]

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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文发表在arXiv上，详细介绍了视觉编码器中图像可记忆性相关性的新发现。[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, other; 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: 120 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.CV TIER_1 English(EN) · Ece Takmaz, Albert Gatt, Jakub Dotlacil · 2026-05-05 04:00

图像可记忆性在视觉编码器中的相关性：激活、注意力熵、斑块均匀性和自编码器损失

arXiv:2509.01453v2 Announce Type: replace Abstract: Images vary in how memorable they are to humans. Inspired by findings from cognitive science and computer vision, we explore correlates of image memorability in pretrained transformer-based vision encoders for the first time. Fo…