DeepAI AI Chat
Log In Sign Up

A Survey of Self-Supervised and Few-Shot Object Detection

by   Gabriel Huang, et al.
Université de Montréal

Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a model on novel (unseen) object classes with little data, it still requires prior training on many labeled examples of base (seen) classes. On the other hand, self-supervised methods aim at learning representations from unlabeled data which transfer well to downstream tasks such as object detection. Combining few-shot and self-supervised object detection is a promising research direction. In this survey, we review and characterize the most recent approaches on few-shot and self-supervised object detection. Then, we give our main takeaways and discuss future research directions.


page 2

page 4

page 5

page 11

page 12


How Well Do Self-Supervised Models Transfer?

Self-supervised visual representation learning has seen huge progress in...

Sample, Crop, Track: Self-Supervised Mobile 3D Object Detection for Urban Driving LiDAR

Deep learning has led to great progress in the detection of mobile (i.e....

Improving Object Detection with Selective Self-supervised Self-training

We study how to leverage Web images to augment human-curated object dete...

An Empirical Study and Comparison of Recent Few-Shot Object Detection Algorithms

The generic object detection (GOD) task has been successfully tackled by...

Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection

Though quite challenging, leveraging large-scale unlabeled or partially ...