PulseAugur
实时 09:26:57
English(EN) Naturalness Predicts but Does Not Cause Transferability in Image Encodings of Real-World Streams

研究发现图像编码的自然度并非可迁移性的原因

研究人员调查了来自真实世界数据流的图像的视觉自然度与其在图像识别模型中的可迁移性之间的关系。他们发现,尽管与自然图像的Fréchet距离(FID)可以预测准确性,但这种相关性并非因果关系。该研究使用了多样化的时间序列数据集WorldStream,并证明了局部结构而非光谱自然度是可迁移性的关键因素。即使经过完全微调,这些编码图像与结构化基线之间的性能差距仍然显著。 AI

影响 研究了非图像数据的图像编码如何影响AI模型性能,表明结构属性是关键。

排序理由 研究论文,详细介绍了新的数据集和关于图像编码可迁移性的实验结果。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

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

研究发现图像编码的自然度并非可迁移性的原因

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Faruk Alpay, Baris Basaran ·

    Naturalness Predicts but Does Not Cause Transferability in Image Encodings of Real-World Streams

    arXiv:2606.25844v1 Announce Type: new Abstract: A common practice converts a one-dimensional signal into an image so that a vision backbone pretrained on natural photographs can be reused for recognition, yet the encoded image is rarely examined. We ask how the visual naturalness…

  2. arXiv cs.CV TIER_1 English(EN) · Baris Basaran ·

    Naturalness Predicts but Does Not Cause Transferability in Image Encodings of Real-World Streams

    A common practice converts a one-dimensional signal into an image so that a vision backbone pretrained on natural photographs can be reused for recognition, yet the encoded image is rarely examined. We ask how the visual naturalness of an encoded image relates to its transfer acc…