Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types

by   Thomas Mensink, et al.

Transfer learning enables to re-use knowledge learned on a source task to help learning a target task. A simple form of transfer learning is common in current state-of-the-art computer vision models, i.e. pre-training a model for image classification on the ILSVRC dataset, and then fine-tune on any target task. However, previous systematic studies of transfer learning have been limited and the circumstances in which it is expected to work are not fully understood. In this paper we carry out an extensive experimental exploration of transfer learning across vastly different image domains (consumer photos, autonomous driving, aerial imagery, underwater, indoor scenes, synthetic, close-ups) and task types (semantic segmentation, object detection, depth estimation, keypoint detection). Importantly, these are all complex, structured output tasks types relevant to modern computer vision applications. In total we carry out over 1200 transfer experiments, including many where the source and target come from different image domains, task types, or both. We systematically analyze these experiments to understand the impact of image domain, task type, and dataset size on transfer learning performance. Our study leads to several insights and concrete recommendations for practitioners.



There are no comments yet.


page 2

page 10

page 11

page 12

page 14

page 19

page 20

page 21


Investigating the Impact of Data Volume and Domain Similarity on Transfer Learning Applications

Transfer Learning helps to build a system to recognize and apply knowled...

Investigation on How Data Volume Affects Transfer Learning Performances in Business Applications

Transfer Learning helps to build a system to recognize and apply knowled...

Domain Adaptive Transfer Learning with Specialist Models

Transfer learning is a widely used method to build high performing compu...

Explicit Domain Adaptation with Loosely Coupled Samples

Transfer learning is an important field of machine learning in general, ...

Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving

Training vision-based autonomous driving in the real world can be ineffi...

COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasets

Transfer learning is a proven technique in 2D computer vision to leverag...

What's Mine is Yours: Pretrained CNNs for Limited Training Sonar ATR

Finding mines in Sonar imagery is a significant problem with a great dea...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.