Better weakly supervised object detection by using absolutely wrong data with NDI-WSOD
Better weakly supervised object detection by using absolutely wrong data with NDI-WSOD
Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information
arXiv paper abstract https://arxiv.org/abs/2204.10068v1
arXiv PDF paper https://arxiv.org/pdf/2204.10068v1.pdf
Weakly supervised object detection (WSOD) is a challenging task, in which image-level labels (e.g., categories of the instances in the whole image) are used to train an object detector.
... discover that negative instances (i.e. absolutely wrong instances), ignored in most of the previous studies, normally contain valuable deterministic information.
... propose a negative deterministic information ... NDI-WSOD ... design several processes to identify and distill the NDI from negative instances online.
... utilize the extracted NDI to construct a novel negative contrastive learning mechanism and a negative guided instance selection strategy for dealing with the issues of part domination and missing instances, respectively.
... method achieves satisfactory performance.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments