AI Paper Atlas

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

Taskonomy: Disentangling Task Transfer Learning

Amir R. Zamir, Alexander Sax, William Shen, Leonidas J. Guibas, Jitendra Malik, Silvio Savarese

CVPR 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 1,182 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
Choose transfers using the computed taxonomy rather than random feasible transfer policiesTaskonomy transfer policies · Visual task dictionaryGain and QualityImproved
Choose target-specific transfer policies rather than fixed transfersTaskonomy transfer policies · Novel visual taskswin rateImproved
Use a surface-normal representation rather than depth as the source for surface-normal/depth-related transferTaskonomy transfer modeling · Depth and surface normalstransfer performanceMixed
Increase the supervision budgetTaskonomy taxonomy · Visual task dictionaryGain and QualityImproved
Add multiple complementary source-task representations to a transferTaskonomy higher-order transfers · Visual task transfertransfer performanceImproved
Use transitive transfers (s → t1 → t2) (ablation)Taskonomy transfer modeling · Visual task transfertransfer performanceNo 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