# Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Active Tasks.

> Research article (arXiv (Cornell University), 2018) · cited 15× · AI/ML

**Wikidata**: [openalex:W2907617375](https://www.wikidata.org/wiki/openalex:W2907617375)  
**Source**: https://4ort.xyz/entity/mid-level-visual-representations-improve-generalization-and-sample-efficiency-for-learning-active-tasks