Decoupling Disease, Covariates, and Individual Variability: A Unified Disentanglement Framework for Medical Image Classification
本文提出MedIDL框架，通过将图像特征映射到三个正交潜在空间来解决医学图像分类中疾病相关特征与混淆变量和个人变异的分离问题。
0 citationsRead paper
Selected work
Representative Papers
An Empirical Study of Data Scale, Model Complexity, and Input Modalities in Visual Generalization
This study systematically investigates the mechanisms by which data scale, model complexity, and input modality influence the generalization performance of vision models. Within a unified experimental framework, the authors conduct controlled and large-scale ablation studies on synthetic functions and the CIFAR dataset, employing polynomial fitting, diverse CNN and Transformer architectures, and multimodal inputs—including RGB, grayscale, gradients, edges, and wavelet representations—to quantitatively compare the effects of these three core factors for the first time. The findings reveal that increasing training data consistently enhances generalization; greater model complexity yields non-monotonic improvements; removing color information substantially degrades performance; and the efficacy of explicit handcrafted priors is highly dependent on model architecture.
0 citationsRead paper
Recent publications
Latest Papers
Decoupling Disease, Covariates, and Individual Variability: A Unified Disentanglement Framework for Medical Image Classification
本文提出MedIDL框架，通过将图像特征映射到三个正交潜在空间来解决医学图像分类中疾病相关特征与混淆变量和个人变异的分离问题。
0 citationsRead paper
An Empirical Study of Data Scale, Model Complexity, and Input Modalities in Visual Generalization
This study systematically investigates the mechanisms by which data scale, model complexity, and input modality influence the generalization performance of vision models. Within a unified experimental framework, the authors conduct controlled and large-scale ablation studies on synthetic functions and the CIFAR dataset, employing polynomial fitting, diverse CNN and Transformer architectures, and multimodal inputs—including RGB, grayscale, gradients, edges, and wavelet representations—to quantitatively compare the effects of these three core factors for the first time. The findings reveal that increasing training data consistently enhances generalization; greater model complexity yields non-monotonic improvements; removing color information substantially degrades performance; and the efficacy of explicit handcrafted priors is highly dependent on model architecture.
0 citationsRead paper