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

Citations Over TimeTop 10% of 2022 papers

Abstract

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. Project page: https://gabrielhuang.github.io/fsod-survey/.

Related Papers

• → A Survey on Semi-supervised Learning for Delayed Partially Labelled Data Streams(2022)59 cited
• → Online transfer learning by leveraging multiple source domains(2017)51 cited
• → Weakly Supervised Transfer Learning for Multi-label Appliance Classification(2022)7 cited
• → Boosting Facial Landmark Detection via Self-supervised and Semi-supervised Learning(2023)1 cited
• → A new semi-supervised inductive transfer learning framework: Co-Transfer(2021)2 cited