Transformation Invariant Cancerous Tissue Classification Using Spatially Transformed DenseNet
This work addresses the challenge of classifying cancerous tissue robustly to transformations, which is incremental as it builds on existing DenseNet methods.
The paper tackled the problem of transformation invariant classification of cancer tissue by introducing a spatially transformed DenseNet architecture, which increased accuracy over the base DenseNet while being simpler than other invariance models.
In this work, we introduce a spatially transformed DenseNet architecture for transformation invariant classification of cancer tissue. Our architecture increases the accuracy of the base DenseNet architecture while adding the ability to operate in a transformation invariant way while simultaneously being simpler than other models that try to provide some form of invariance.