Forward-Forward Contrastive Learning
This work addresses the problem of improving disease classification from medical images for computer-aided diagnosis, but it is incremental as it builds on existing pretraining and contrastive learning methods.
The paper tackled the challenge of constructing generalized and robust medical image classifications by proposing Forward-Forward Contrastive Learning (FFCL), a novel pretraining approach that leverages the Forward-Forward Algorithm in a contrastive learning framework, achieving a 3.69% accuracy improvement over ImageNet pretrained ResNet-18 on a chest X-ray pneumonia classification task.
Medical image classification is one of the most important tasks for computer-aided diagnosis. Deep learning models, particularly convolutional neural networks, have been successfully used for disease classification from medical images, facilitated by automated feature learning. However, the diverse imaging modalities and clinical pathology make it challenging to construct generalized and robust classifications. Towards improving the model performance, we propose a novel pretraining approach, namely Forward Forward Contrastive Learning (FFCL), which leverages the Forward-Forward Algorithm in a contrastive learning framework--both locally and globally. Our experimental results on the chest X-ray dataset indicate that the proposed FFCL achieves superior performance (3.69% accuracy over ImageNet pretrained ResNet-18) over existing pretraining models in the pneumonia classification task. Moreover, extensive ablation experiments support the particular local and global contrastive pretraining design in FFCL.