Hongyang Yu

Y. Logan, K. Kokilepersaud, G. Kwon et al.

In this paper, we propose a framework that incorporates experts diagnostics and insights into the analysis of Optical Coherence Tomography (OCT) using multi-modal learning. To demonstrate the effectiveness of this approach, we create a medical diagnostic attribute dataset to improve disease classification using OCT. Although there have been successful attempts to deploy machine learning for disease classification in OCT, such methodologies lack the experts insights. We argue that injecting ophthalmological assessments as another supervision in a learning framework is of great importance for the machine learning process to perform accurate and interpretable classification. We demonstrate the proposed framework through comprehensive experiments that compare the effectiveness of combining diagnostic attribute features with latent visual representations and show that they surpass the state-of-the-art approach. Finally, we analyze the proposed dual-stream architecture and provide an insight that determine the components that contribute most to classification performance.

Wenzhao Xiang, Chang Liu, Hang Su et al.

Masked image modeling (MIM) has gained significant traction for its remarkable prowess in representation learning. As an alternative to the traditional approach, the reconstruction from corrupted images has recently emerged as a promising pretext task. However, the regular corrupted images are generated using generic generators, often lacking relevance to the specific reconstruction task involved in pre-training. Hence, reconstruction from regular corrupted images cannot ensure the difficulty of the pretext task, potentially leading to a performance decline. Moreover, generating corrupted images might introduce an extra generator, resulting in a notable computational burden. To address these issues, we propose to incorporate adversarial examples into masked image modeling, as the new reconstruction targets. Adversarial examples, generated online using only the trained models, can directly aim to disrupt tasks associated with pre-training. Therefore, the incorporation not only elevates the level of challenge in reconstruction but also enhances efficiency, contributing to the acquisition of superior representations by the model. In particular, we introduce a novel auxiliary pretext task that reconstructs the adversarial examples corresponding to the original images. We also devise an innovative adversarial attack to craft more suitable adversarial examples for MIM pre-training. It is noted that our method is not restricted to specific model architectures and MIM strategies, rendering it an adaptable plug-in capable of enhancing all MIM methods. Experimental findings substantiate the remarkable capability of our approach in amplifying the generalization and robustness of existing MIM methods. Notably, our method surpasses the performance of baselines on various tasks, including ImageNet, its variants, and other downstream tasks.