Country
InDefenseoftheUnitaryScalarization forDeepMulti-TaskLearning
While some workshowsthatmulti-task networkstrained viaunitary scalarization exhibit superior performance to independent per-task models [29, 35], others suggest the opposite [30, 54, 58]. However, SMTOs usually require access to per-task gradients either with respect to the shared parameters, or to the shared representation.
7137debd45ae4d0ab9aa953017286b20-Paper.pdf
Previouswork onneural 3Dreconstruction demonstrated benefits, butalso limitations, ofpoint cloud, voxel, surface mesh, and implicit function representations. Unlike existing volumetric approaches,DEFTET optimizes for both vertex placement and occupancy, and is differentiable with respect to standard 3D reconstruction lossfunctions.