Improved Region Proposal Network for Enhanced Few-Shot Object Detection

by   Zeyu Shangguan, et al.

Despite significant success of deep learning in object detection tasks, the standard training of deep neural networks requires access to a substantial quantity of annotated images across all classes. Data annotation is an arduous and time-consuming endeavor, particularly when dealing with infrequent objects. Few-shot object detection (FSOD) methods have emerged as a solution to the limitations of classic object detection approaches based on deep learning. FSOD methods demonstrate remarkable performance by achieving robust object detection using a significantly smaller amount of training data. A challenge for FSOD is that instances from novel classes that do not belong to the fixed set of training classes appear in the background and the base model may pick them up as potential objects. These objects behave similarly to label noise because they are classified as one of the training dataset classes, leading to FSOD performance degradation. We develop a semi-supervised algorithm to detect and then utilize these unlabeled novel objects as positive samples during the FSOD training stage to improve FSOD performance. Specifically, we develop a hierarchical ternary classification region proposal network (HTRPN) to localize the potential unlabeled novel objects and assign them new objectness labels to distinguish these objects from the base training dataset classes. Our improved hierarchical sampling strategy for the region proposal network (RPN) also boosts the perception ability of the object detection model for large objects. We test our approach and COCO and PASCAL VOC baselines that are commonly used in FSOD literature. Our experimental results indicate that our method is effective and outperforms the existing state-of-the-art (SOTA) FSOD methods. Our implementation is provided as a supplement to support reproducibility of the results.


page 9

page 12

page 15

page 24


Identification of Novel Classes for Improving Few-Shot Object Detection

Conventional training of deep neural networks requires a large number of...

Meta-Cognition-Based Simple And Effective Approach To Object Detection

Recently, many researchers have attempted to improve deep learning-based...

Prototypical Region Proposal Networks for Few-Shot Localization and Classification

Recently proposed few-shot image classification methods have generally f...

Self-Trained Proposal Networks for the Open World

Deep learning-based object proposal methods have enabled significant adv...

ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection

Few-shot object detection (FSOD) identifies objects from extremely few a...

Cooperating RPN's Improve Few-Shot Object Detection

Learning to detect an object in an image from very few training examples...

Open-Set Object Detection Using Classification-free Object Proposal and Instance-level Contrastive Learning with Appendix

Detecting both known and unknown objects is a fundamental skill for robo...

Please sign up or login with your details

Forgot password? Click here to reset