AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation

Jogendra Nath Kundu, Nishank Lakkakula, R. Venkatesh Babu

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 57 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
use CCR instead of FCF content regularizer (ablation)UM-Adapt-B · NYUD-v2 depthrel error: 0.218 -> 0.192Mixed
use CCR instead of FCF content regularizer (ablation)UM-Adapt-B · NYUD-v2 segmentationmean IoU: 0.154 -> 0.163Improved
use CCR instead of FCF content regularizer (ablation)UM-Adapt-B · NYUD-v2 surface normalsmean angle error: 24.6 -> 23.8Improved
add cross-task distillation from frozen task-transfer networks (ablation)UM-Adapt-B(CCR) · NYUD-v2 segmentationmean IoU: 0.163 -> 0.214Improved
add cross-task distillation from frozen task-transfer networks (ablation)UM-Adapt-B(CCR) · NYUD-v2 depthrel error: 0.192 -> 0.178Improved
use two task-transfer networks instead of one (ablation)UM-Adapt-(noAdv.) · NYUD-v2 segmentationmean IoU: 0.189 -> 0.214Improved
use two task-transfer networks instead of one (ablation)UM-Adapt-(noAdv.) · NYUD-v2 depthrel error: 0.181 -> 0.178Improved
add adversarial update of task-transfer networks (ablation)UM-Adapt-(noAdv.) · NYUD-v2 segmentationmean IoU: 0.214 -> 0.221Improved
add adversarial update of task-transfer networks (ablation)UM-Adapt-(noAdv.) · Cityscapes segmentationmean IoU: 0.408 -> 0.420Improved
add adversarial update of task-transfer networks (ablation)UM-Adapt-(noAdv.) · KITTI depthrel error: 0.28 -> 0.27Improved
add adversarial update of task-transfer networks (ablation)UM-Adapt-(noAdv.) · training stabilitystabilityHurt
add multi-task adaptation (UM-Adapt-(Adv.)) to source-only baselineMulti-task baseline · NYUD-v2 segmentationmean IoU: 0.022 -> 0.221Improved

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