Accomplishments
Improvising Weakly Supervised Object Detection using Deep Learning Techniques
Category
Articles
Authors
Publisher
Blue Eyes Intelligence Engineering & Sciences Publ
Publishing Date
01-Feb-2020
volume
9
Issue
3
Pages
728-738
- Abstract
Object detection is closely related with video and image analysis. Under computer vision technology, object detection model training with image-level labels only is challenging research area. Researchers have not yet discovered an accurate model for Weakly Supervised Object Detection (WSOD). WSOD is used for detecting and localizing the objects under the supervision of image-level annotations only. The proposed work uses a self-paced approach which is applied on region proposal network of Faster R-CNN architecture which gives a better solution from the previous weakly supervised object detectors and it can be applied for computer vision applications in near future.