AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Task Switching Network for Multi-Task Learning

Guolei Sun, Thomas Probst, Danda Pani Paudel, Nikola Popović, Menelaos Kanakis, Jagruti Patel, Dengxin Dai, Luc Van Gool

ICCV 2021 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 44 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 task embedding network (learned AdaIN coefficients) to task-specific INs (ablation)TSN decoder · PASCAL-Context (5 tasks)Delta_m %: 1.43 -> 0.30Improved
use instance normalization instead of batch normalization for task-specific affine parameters (ablation)TSN decoder · PASCAL-Context (5 tasks)Delta_m %: 4.38 -> 1.43Improved
replace multi-decoder with single shared conditional decoder (INs+TE)TSN · PASCAL-Context (5 tasks)Delta_m %: 4.32 -> 0.30Improved
increase orthogonal task-code dimension from 100 to 250 (ablation)TSN task embedding · PASCAL-Context (5 tasks)Delta_m %: 0.30 -> 0.75Hurt
use Gaussian instead of orthogonal task codes at d=100 (ablation)TSN task embedding · PASCAL-Context (5 tasks)Delta_m %: 0.30 -> 1.22Hurt
use Gaussian instead of orthogonal task codes at d=50 (ablation)TSN task embedding · PASCAL-Context (5 tasks)Delta_m %: 0.32 -> 0.30No clear effect
scale backbone from ResNet-18 to ResNet-34 (ablation)TSN · PASCAL-Context (5 tasks)Delta_m %: 0.30 -> 0.99Hurt
scale backbone from ResNet-18 to ResNet-101 (ablation)TSN · PASCAL-Context (5 tasks)Delta_m %: 0.30 -> 0.93Hurt
compare TSN with RCM on PASCAL-ContextTSN · PASCAL-Context (5 tasks)Delta_m %: 3.62 -> 0.30Improved
compare TSN with RCM on NYUDTSN · NYUD (4 tasks)Delta_m %: 6.14 -> 0.03Improved
convert TSN to task-conditioned network by precomputing AdaIN parametersTSN · PASCAL-Context (5 tasks)# params: 18.3M -> 17.7MImproved
share one prediction head across tasks instead of separate heads (ablation)TSN · PASCAL-Context (5 tasks)accuracyNo clear effect

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