Title: Dataset Distillation for Super-Resolution without Class Labels and Pre-trained Models Show Chinese title

Title: 无类别标签和预训练模型的超分辨率数据集蒸馏

Abstract: Training deep neural networks has become increasingly demanding, requiring large datasets and significant computational resources, especially as model complexity advances. Data distillation methods, which aim to improve data efficiency, have emerged as promising solutions to this challenge. In the field of single image super-resolution (SISR), the reliance on large training datasets highlights the importance of these techniques. Recently, a generative adversarial network (GAN) inversion-based data distillation framework for SR was proposed, showing potential for better data utilization. However, the current method depends heavily on pre-trained SR networks and class-specific information, limiting its generalizability and applicability. To address these issues, we introduce a new data distillation approach for image SR that does not need class labels or pre-trained SR models. In particular, we first extract high-gradient patches and categorize images based on CLIP features, then fine-tune a diffusion model on the selected patches to learn their distribution and synthesize distilled training images. Experimental results show that our method achieves state-of-the-art performance while using significantly less training data and requiring less computational time. Specifically, when we train a baseline Transformer model for SR with only 0.68\% of the original dataset, the performance drop is just 0.3 dB. In this case, diffusion model fine-tuning takes 4 hours, and SR model training completes within 1 hour, much shorter than the 11-hour training time with the full dataset. Show Chinese abstract

Abstract: 训练深度神经网络变得越来越具有挑战性，需要大量数据集和显著的计算资源，尤其是在模型复杂度不断提高的情况下。旨在提高数据效率的数据蒸馏方法已成为解决这一挑战的有前景的方案。在单图像超分辨率（SISR）领域，对大规模训练数据集的依赖凸显了这些技术的重要性。最近，提出了一种基于生成对抗网络（GAN）逆向的数据蒸馏框架用于SR，显示出更好的数据利用潜力。然而，当前方法严重依赖预训练的SR网络和类别特定信息，限制了其泛化能力和适用性。为了解决这些问题，我们引入了一种新的图像SR数据蒸馏方法，该方法不需要类别标签或预训练的SR模型。具体来说，我们首先提取高梯度块，并根据CLIP特征对图像进行分类，然后在选定的块上微调扩散模型，以学习其分布并合成蒸馏的训练图像。实验结果表明，我们的方法在使用显著更少的训练数据和更少计算时间的情况下实现了最先进的性能。具体而言，当仅使用原始数据集的0.68%来训练基准Transformer模型时，性能下降仅为0.3 dB。在这种情况下，扩散模型微调需要4小时，而SR模型训练在1小时内完成，远短于使用完整数据集的11小时训练时间。