Yes, IoU loss is submodular - as a function of the mispredictions
arXiv:1809.01845v12 citations
AI Analysis
This clarifies a theoretical point in machine learning for researchers working on segmentation and loss functions, but it is incremental as it only addresses a specific dispute.
The authors refute a claim that a previous proposition about IoU loss is false, demonstrating that the assertion was based on a misreading of set membership and affirming the proposition's truth.
This note is a response to [7] in which it is claimed that [13, Proposition 11] is false. We demonstrate here that this assertion in [7] is false, and is based on a misreading of the notion of set membership in [13, Proposition 11]. We maintain that [13, Proposition 11] is true. ([7] = arXiv:1809.00593, [13] = arXiv:1512.07797)