发表机构
Gdańsk University of Technology; Medical University of Gdańsk（格但斯克工业大学; 格但斯克医科大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出双层级关系框架，结合隐式图像块关系建模与显式图结构消息传递，在ISIC-2018、ISIC-2019皮肤病变诊断基准上提升了平衡准确率，其中集成网格结构的图注意力网络表现最优。
AI 中文摘要
关系归纳偏差对于捕捉数据间的结构依赖至关重要。本研究针对图像分类探究了一种双层级关系框架，弥合了隐式表示学习与显式结构建模之间的差距。我们首先使用EfficientNetB3架构建立基线。为突破标准卷积偏差的局限，我们采用基于图像块的策略，利用卷积掩码自动编码器通过自监督重构学习图像块间的隐式关系。随后，我们扩展该方法，纳入显式关系建模，将学习到的嵌入组织为多种图拓扑结构，包括基于网格、随机及k近邻结构。在ISIC-2018和ISIC-2019皮肤病变诊断基准上的实验结果表明，结合隐式图像块间建模与显式基于图的消息传递可取得最佳性能。在ISIC-2018测试集上，基线模型的平衡准确率为76.17%，采用隐式基于图像块的关系建模后提升至77.12%；完全集成网格结构的图注意力网络进一步将性能提升至79.27%。类似地，在ISIC-2019上，隐式方法达到59.84%的平衡准确率，而隐式与显式建模的结合则取得60.67%的平衡准确率。
英文摘要
Relational inductive biases are essential for capturing structural dependencies among data. This study investigates a dual-level relational framework for image classification, bridging the gap between implicit representation learning and explicit structural modelling. We begin by establishing a baseline using an EfficientNetB3 architecture. To move beyond standard convolutional biases, we adopt a patch-based strategy, employing a convolutional masked autoencoder to learn implicit inter-patch relationships through self-supervised reconstruction. We then extend this approach by incorporating explicit relational modelling, organizing the learned embeddings into various graph topologies, including grid-based, random, and k-nearest neighbour structures. Experimental results on the ISIC-2018 and ISIC-2019 skin lesion diagnosis benchmarks show that combining implicit inter-patch modelling with explicit graph-based message passing yields the best performance. On the ISIC-2018 test set, the baseline model achieves a balanced accuracy of 76.17%, which improves to 77.12% with implicit patch-based relational modelling. The fully integrated grid-structured Graph Attention Network further increases performance to 79.27%. Similarly, on ISIC-2019, the implicit approach reaches 59.84% balanced accuracy, while the combination of implicit and explicit modelling yields 60.67%.
CommentsAccepted as a short paper for presentation at the 21st International Conference on Computational Intelligence Methods for Bioinformatics and Biostatistics (CIBB 2026)
