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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Choose transfers using the computed taxonomy rather than random feasible transfer policies | Taskonomy transfer policies · Visual task dictionary | Gain and Quality | Improved |
| Choose target-specific transfer policies rather than fixed transfers | Taskonomy transfer policies · Novel visual tasks | win rate | Improved |
| Use a surface-normal representation rather than depth as the source for surface-normal/depth-related transfer | Taskonomy transfer modeling · Depth and surface normals | transfer performance | Mixed |
| Increase the supervision budget | Taskonomy taxonomy · Visual task dictionary | Gain and Quality | Improved |
| Add multiple complementary source-task representations to a transfer | Taskonomy higher-order transfers · Visual task transfer | transfer performance | Improved |
| Use transitive transfers (s → t1 → t2) (ablation) | Taskonomy transfer modeling · Visual task transfer | transfer performance | No clear effect |
Closest papers by meaning
- Understanding the Transferability of Representations via Task-Relatedness (NeurIPS 2024 · similarity 0.90)
- Understanding Task Transfer in Vision-Language Models (CVPR 2026 · similarity 0.88)
- Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models (ICML 2024 · similarity 0.87)
- Towards Principled Task Grouping for Multi-Task Learning (NeurIPS 2026 · similarity 0.87)
- Interpreting Object-level Foundation Models via Visual Precision Search (CVPR 2025 · similarity 0.86)
- Going Beyond Multi-Task Dense Prediction with Synergy Embedding Models (CVPR 2024 · similarity 0.86)
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.
