Combining loss-scale and gradient-magnitude balancing achieves Δp = +1.15±0.16 on NYUv2.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Using only loss-scale balancing (log transformation) yields Δp = +0.06±0.09 on NYUv2.finding0.898
  Ablation study component effectiveness.
• The gradient-magnitude balancing method outperforms GradNorm on NYUv2, Cityscapes, Office-31, Office-Home.finding0.788
  Comparison of gradient-magnitude balancing with GradNorm.
• DB-MTL achieves ∆p = +1.15±0.16 on NYUv2, outperforming all baselines including state-of-the-artfinding0.783
  Primary empirical validation on scene understanding task
• The proposed gradient-magnitude balancing method consistently outperforms GradNorm, as it guarantees equal gradient magnitudes and considers update magnitude.claim0.780
  Advantage over GradNorm.
• DB-MTL has similar per-epoch running time to gradient balancing methods on NYUv2, slower than loss balancing methods.finding0.776
  Computational efficiency comparison.
• Task balancing requires simultaneous consideration of both loss scales and gradient magnitudesclaim0.764
  Core interpretive position of DB-MTL: complementarity of loss and gradient perspectives
• DB-MTL training losses decrease smoothly and gradient norms are lower than EW on NYUv2, indicating training stability.finding0.762
  Training stability analysis.
• DB-MTL achieves loss-scale balancing by performing logarithm transformation on each task loss, and rescales gradient magnitudes by normalizing all task gradients to comparable magnitudes using the maximum gradient norm.quote0.758
  Concise summary of the DB-MTL method from the abstract.