以离散扩散分类建模推进图像分类
Advancing Image Classification with Discrete Diffusion Classification Modeling
把扩散过程从生成图像迁移到类别标签空间，用少步扩散迭代对类别后验做去噪式推断，可作为即插即用的分类头替换标准 softmax 分类器，在图像损坏或训练数据稀缺时提升鲁棒性。
原文依据 leverages a diffusion-based procedure to model the posterior distribution of class labels conditioned on the input image
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图像分类是计算机视觉中研究充分的任务，但在高不确定性条件下（例如输入图像被损坏或训练数据有限时）仍然具有挑战性。传统分类方法通常训练模型直接从输入图像预测类别标签，但在上述场景中这可能导致次优性能。为解决该问题，我们提出离散扩散分类建模（DiDiCM），这是一个新颖的框架，利用基于扩散的过程对以输入图像为条件的类别标签后验分布进行建模。DiDiCM 支持在类别概率或离散类别标签上进行基于扩散的预测，从而在计算与内存的权衡上提供灵活性。我们开展了全面的实证研究，证明 DiDiCM 优于标准分类器：在 ImageNet 数据集上，少量扩散迭代即可取得高于基线的分类准确率，且随着任务难度增加，准确率提升幅度也随之增大。代码已发布于 https://github.com/omerb01/didicm。
英文原文摘要 1145 字符
Image classification is a well-studied task in computer vision, and yet it remains challenging under high-uncertainty conditions, such as when input images are corrupted or training data are limited. Conventional classification approaches typically train models to directly predict class labels from input images, but this might lead to suboptimal performance in such scenarios. To address this issue, we propose Discrete Diffusion Classification Modeling (DiDiCM), a novel framework that leverages a diffusion-based procedure to model the posterior distribution of class labels conditioned on the input image. DiDiCM supports diffusion-based predictions either on class probabilities or on discrete class labels, providing flexibility in computation and memory trade-offs. We conduct a comprehensive empirical study demonstrating the superior performance of DiDiCM over standard classifiers, showing that a few diffusion iterations achieve higher classification accuracy on the ImageNet dataset compared to baselines, with accuracy gains increasing as the task becomes more challenging. We release our code at https://github.com/omerb01/didicm.