AI Paper Atlas

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

TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts

Hanrong Ye, Dan Xu

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 55 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
add MoE (experts and task gating) to the multi-task baseline (ablation)TaskExpert (ViT-B) · PASCAL-ContextSemseg mIoU: 76.40 -> 77.62 (+1.22)Improved
add context-aware gating to MoE (ablation)TaskExpert (ViT-B) · PASCAL-ContextBoundary odsF: 70.40 -> 71.70 (+1.30)Improved
add multi-task feature memory (ablation)TaskExpert (ViT-B) · PASCAL-ContextMTL Perf Delta_m: -2.07 -> -1.46Improved
use dense instead of sparse (top-1, top-2) expert activation (ablation)TaskExpert · PASCAL-Contextmulti-task performanceImproved
use 3x3 instead of 1x1 gating convolution kernel (ablation)TaskExpert gating · PASCAL-ContextSemseg mIoU: 77.73 -> 78.45 (+0.72)Improved
increase gating kernel from 3x3 to 5x5 (ablation)TaskExpert gating · PASCAL-ContextSemseg mIoU: 78.45 -> 78.40No clear effect
replace MLP gating with context-aware gating (ablation)TaskExpert · PASCAL-ContextMTL Perf Delta_m: -2.96 -> -2.07Improved
use 12 MMoE modules instead of 3 or 6 (ablation)TaskExpert (ViT-B) · PASCAL-ContextSemseg mIoU: 78.04 -> 78.45Improved
TaskExpert versus InvPT with ViT-L backboneTaskExpert · PASCAL-ContextSemseg mIoU: 79.03 -> 80.64Improved
TaskExpert versus InvPT with ViT-L backboneTaskExpert · NYUD-v2Semseg mIoU: 53.56 -> 55.35Improved
TaskExpert ViT-S versus Mod-SquadTaskExpert ViT-S · PASCAL-Context (ViT-S)multi-metric: Semseg 74.10 -> 75.04; Boundary 72.00 -> 68.80Mixed

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