This study compares feature maps produced by semantic segmentation architectures using varying combinations of convolutional neural network (CNN), Transformer, and Mamba selective 26 state space (selective SSM) components with a goal of exploring the following question: does correlation or similarity between the generated data abstractions imply comparable predictive performance?
A novel adaptive fusion framework that adaptively combines CNN and Transformer features through learnable gating, attention-based feature integration, and explainable-AI methods is developed, intended to improve both computational efficiency and model interpretability.
Komal Sharma, Monika Sainger· International journal of com...· 0 citations
The results show that larger models and larger pretraining datasets do not automatically lead to better downstream performance, and transfer effectiveness in medical imaging is driven primarily by architectural inductive biases, pretraining strategy, and domain relevance.
Dina A. Elkholy, Mohamed S. Shehata, John W. Braun· Journal of imaging informati...· 0 citations
Medical image classification is fundamental to computer-aided diagnosis. Limited labeled samples, subtle inter-class differences, and heterogeneous lesion morphology make it difficult for a single representation to capture all relevant cues. This study investigates MedFuse, a simple dual-stream framework that combi...
Ya-Jing Ren, Hai Ling, Zheng Gu et al.· Frontiers in Medicine· 0 citations
A hybrid Neural Network-Transformer encoder trained on four complimentary datasets maintains competitive accuracy across all four datasets while producing more retrieval-relevant embeddings and much more consistent performance under degraded queries suggests that the model may serve as a promising foundation for future...
TransCat, a hybrid CNN-Transformer architecture for medical image segmentation, is proposed and an extended deformable attention mechanism with attentive value identification is developed, to control the computational burden caused by the enlarged token set.
Jin Wang, Zheng-Hua Yang, Dong-Ming Zhou et al.· Frontiers in Bioinformatics· 0 citations
A new method is presented for explaining CNNs and ViTs image classification through a set of interpretable rules composed of one or more antecedents, which combine pixel-level properties and patch-level features, analyzing the impact of each region on the model’s classification.
Jean-Marc Boutay, Damian Boquete, Deniz Köprülü et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
