Reverse Error Modeling for Improved Semantic Segmentation
We propose the concept of error-reversing autoencoders (ERA) for correcting pixel-wise errors made by an arbitrary semantic segmentation model. For this, we reframe the …
Christopher Kuhn
We propose the concept of error-reversing autoencoders (ERA) for correcting pixel-wise errors made by an arbitrary semantic segmentation model. For this, we reframe the …