潜在空间中的有效秩作为图像复杂度和丰富度度量
ERank in Latent Space as an Image-Complexity and Richness Measure
浏览论文内容
中文总结 AI 辅助
研究提出用图像深度特征图通道协方差的ERank衡量视觉丰富度，经单次前向传播计算得出。它能排序图像，与多种指标相关，与人类标注有一定关联。作为数据选择标准，对超分辨率、OCR等任务有不同影响，是受输入丰富度影响时有用的廉价信号。
中文摘要 AI 辅助
我们提出将图像深度特征图的通道协方差的有效秩（ERank）作为一种无标签的视觉丰富度度量，它通过单次前向传播经过冻结的预训练编码器计算得出。ERank计算图像激活的去相关通道方向数量，并对其性质进行了刻画。实验表明，ERank能对图像从简单到视觉丰富进行排序，与编解码比特率、清晰度和边缘密度相关，与人类对IC9600的复杂度标注的相关系数为0.72。作为数据选择标准，去除低ERank样本可改善超分辨率，去除高ERank样本可改善OCR，而选择对分类、分割或去噪无帮助。因此，ERank是一种廉价的丰富度信号，在任务难度受输入丰富度影响时很有用。
英文摘要
We propose the effective rank (ERank) of the channel covariance of an image's deep feature map as a per-sample, label-free measure of visual richness, computed from a single forward pass through a frozen pretrained encoder. ERank counts how many decorrelated channel directions an image activates, and we characterize its properties, including its behavior under noise. Empirically, ERank orders images from plain to visually rich, correlates with codec bitrate, sharpness, and edge density, and correlates with human complexity annotations on IC9600 with $r = 0.72$. As a data-selection criterion, removing low-ERank samples improves super-resolution and removing high-ERank samples improves OCR, in both pretraining and finetuning, while selection does not help classification, segmentation, or denoising. ERank is thus a cheap richness signal, useful exactly when task difficulty is governed by input richness.
