Goto

Collaborating Authors

 Country



InDefenseoftheUnitaryScalarization forDeepMulti-TaskLearning

Neural Information Processing Systems

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

Neural Information Processing Systems

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.