改进随机裁剪方式，让对比学习更准地保留图像标签
Taming the Randomness: Towards Label-Preserving Cropping in Contrastive Learning
- 设计可参数化的裁剪方法，减少随机裁剪带来的语义失真
- 在CIFAR-10上提升2.7%到12.4%的分类准确率
- 适合做自监督学习和对比学习的视觉模型研究者
对比学习（CL）作为自监督学习（SSL）的重要方法，在计算机视觉领域广泛应用。它通过比较同一图像的不同随机增强（如不同裁剪）来实现自标注。然而，随机增强尤其是随机裁剪可能导致图像语义与原图差异过大，引发错误标注，削弱方法效果。本文提出两种新型可参数化裁剪方法，增强自标注鲁棒性，从而提升模型性能。实验表明，相比非参数化随机裁剪，在下游分类任务中，模型准确率提升2.7%至12.4%，具体取决于裁剪尺寸。
原文摘要 · Abstract (English)
Contrastive learning (CL) approaches have gained great recognition as a very successful subset of self-supervised learning (SSL) methods. SSL enables learning from unlabeled data, a crucial step in the advancement of deep learning, particularly in computer vision (CV), given the plethora of unlabeled image data. CL works by comparing different random augmentations (e.g., different crops) of the same image, thus achieving self-labeling. Nevertheless, randomly augmenting images and especially random cropping can result in an image that is semantically very distant from the original and therefore leads to false labeling, hence undermining the efficacy of the methods. In this research, two novel parameterized cropping methods are introduced that increase the robustness of self-labeling and consequently increase the efficacy. The results show that the use of these methods significantly improves the accuracy of the model by between 2.7\% and 12.4\% on the downstream task of classifying CIFAR-10, depending on the crop size compared to that of the non-parameterized random cropping method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。