finding

active

finding:db-mtl-with-segnet-backbone-achieves-p-8-91-on-nyuv2-best-among-all-methods

DB-MTL with SegNet backbone achieves Δp = +8.91 on NYUv2, best among all methods.

Performance with a different backbone network.

Source paper

extracted_from

Dual-Balancing for Multi-Task Learning

(2023) · Baijiong Lin · Weisen Jiang · Feiyang Ye · Yu Zhang +5

Neighborhood — ranked by edge-count

Communities (3)

community

Dual-balancing multi-task learning
members_of
DB-MTL jointly balances loss scale and gradient magnitude, benchmarked on NYUv2 and Office-31.
Dual balancing multi-task learning
members_of
DB-MTL combines loss-scale and gradient-magnitude balancing, benchmarked across NYUv2, Cityscapes, QM9, and Office datasets.
Dynamic balancing for multi-task learning
members_of
Explores gradient/loss balancing techniques with exponential moving average forgetting rates, evaluated on dense prediction tasks like semantic segmentation.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

DB-MTL achieves ∆p = +1.15±0.16 on NYUv2, outperforming all baselines including state-of-the-artfinding0.872
Primary empirical validation on scene understanding task
Using only loss-scale balancing (log transformation) yields Δp = +0.06±0.09 on NYUv2.finding0.772
Ablation study component effectiveness.
On Qwen3-1.7B, MDS achieves ϕ1,C,↑ = 5.0 (SJTs) vs P2 at 4.7, and ϕ1,C,↓ = 1.4 (SJTs) vs P2 at 3.6finding0.757
Specific consciousness sweep result for Qwen3-1.7B from Table 6 demonstrating strong bidirectional steering
Combining loss-scale and gradient-magnitude balancing achieves Δp = +1.15±0.16 on NYUv2.finding0.753
Full DB-MTL ablation result.
DB-MTL has similar per-epoch running time to gradient balancing methods on NYUv2, slower than loss balancing methods.finding0.751
Computational efficiency comparison.
DB-MTL increases gradient cosine similarity faster and keeps it positive on Office-31, reducing gradient conflict vs EW.finding0.737
Analysis of gradient conflict reduction.
DB-MTL training losses decrease smoothly and gradient norms are lower than EW on NYUv2, indicating training stability.finding0.733
Training stability analysis.
DB-MTL with EMA forgetting rate β in a wide range performs better than without EMA (β=0) on Office-31.finding0.729
Effect of EMA forgetting rate on performance.