CEIR：基于概念的可解释图像表示学习
CEIR: Concept-based Explainable Image Representation Learning
AI总结：
针对自监督图像表示可解释性差、验证有偏差的问题，提出CEIR方法，结合CBM、CLIP与GPT-4生成的概念构建可解释表示，在聚类基准上达SOTA，还能免微调提取开放世界图像概念。
摘要：
在现代机器学习领域，利用自监督学习在不依赖标签的情况下获取高质量表示的发展趋势已受到广泛关注。然而，标签信息的缺失，再加上其固有的高维特性，加大了对所学表示进行解释的难度。因此，间接评估成为衡量这些特征质量的常用指标，导致对所学表示原理的验证存在偏差。为应对这些挑战，我们提出了一种名为基于概念的可解释图像表示（CEIR）的新方法。首先，我们借助结合了预训练CLIP的基于概念的模型（CBM）以及由GPT-4生成的概念，将输入图像投影到概念向量空间中。随后，变分自编码器（VAE）从这些投影后的概念中学习潜在表示，以此作为最终的图像表示。由于该表示能够封装高层的、语义相关的概念，模型可将特征归因于人类可理解的概念空间。这不仅提升了可解释性，还保留了下游任务所需的鲁棒性。例如，我们的方法在CIFAR10、CIFAR100和STL10等基准测试上展现出了最优的无监督聚类性能。此外，借助人类概念理解的通用性，CEIR无需微调即可从开放世界图像中无缝提取相关概念，为自动标签生成和标签操作提供了全新的思路。
英文摘要：
In modern machine learning, the trend of harnessing self-supervised learning to derive high-quality representations without label dependency has garnered significant attention. However, the absence of label information, coupled with the inherently high-dimensional nature, improves the difficulty for the interpretation of learned representations. Consequently, indirect evaluations become the popular metric for evaluating the quality of these features, leading to a biased validation of the learned representation rationale. To address these challenges, we introduce a novel approach termed Concept-based Explainable Image Representation (CEIR). Initially, using the Concept-based Model (CBM) incorporated with pretrained CLIP and concepts generated by GPT-4, we project input images into a concept vector space. Subsequently, a Variational Autoencoder (VAE) learns the latent representation from these projected concepts, which serves as the final image representation. Due to the capability of the representation to encapsulate high-level, semantically relevant concepts, the model allows for attributions to a human-comprehensible concept space. This not only enhances interpretability but also preserves the robustness essential for downstream tasks. For instance, our method exhibits state-of-the-art unsupervised clustering performance on benchmarks such as CIFAR10, CIFAR100, and STL10. Furthermore, capitalizing on the universality of human conceptual understanding, CEIR can seamlessly extract the related concept from open-world images without fine-tuning. This offers a fresh approach to automatic label generation and label manipulation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
