AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning

Junguang Jiang, Baixu Chen, Junwei Pan, Ximei Wang, Dapeng Liu, jie jiang, Mingsheng Long

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 6 citations (OpenAlex)

This paper tried a common change: Add a reconstruction / auxiliary loss

add auxiliary task with gradient conflicts · DomainNet Painting/Quickdraw · transfer gain No clear effect

What 987 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace equal-weight joint training with ForkMergejoint training · DomainNet Quickdrawaccuracy: 50.8 -> 73.0Improved
replace equal weighting with ForkMergeDomainNet joint training · DomainNetDelta_m: -9.62% -> +2.00%Improved
ForkMerge vs single-task learningResNet-101 · DomainNetaverage accuracy: 69.8 -> 71.1Improved
pretrain on all tasks then finetune (Post-train)STL · DomainNetaverage accuracy: 69.8 -> 70.4Improved
replace EW with ForkMergeDeepLabV3+ · NYUv2Delta_m: 0.30% -> 4.03%Improved
add task selection with 3 branches (ForkMerge++) (ablation)ForkMerge · NYUv2Delta_m: 4.03% -> 4.59%Improved
increase branches from 2 to 3 (ablation)ForkMerge · DomainNetDelta_m: 2.0% -> 3.0%Improved
increase branches from 3 to 6 (ablation)ForkMerge · DomainNetDelta_m: 3.0% -> 3.6%Improved
gain per added branch as branches increase (ablation)ForkMerge · DomainNetDelta_m/(B-1): 2.0% -> 0.7%Hurt
ForkMerge vs STL on AliExpressESMM · AliExpressaverage AUC: 0.7963 -> 0.8067Improved
equal weighting vs STLESMM · AliExpressDelta_m: -0.39%Hurt
ForkMerge replaces fixed-weight grid search for S4LS4L · CIFAR-10 4000 labelstest error: 13.8 -> 13.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy