Train object detector by labeling only 1 point of object with NSS
Train object detector by labeling only 1 point of object with NSS
Weakly-Supervised Salient Object Detection Using Point Supervison
arXiv paper abstract https://arxiv.org/abs/2203.11652v1
arXiv PDf paper https://arxiv.org/pdf/2203.11652v1.pdf
Current … saliency detection models rely … on large datasets of accurate pixel-wise annotations, but manually labeling pixels is time-consuming
… some weakly supervised methods … alleviating the problem, such as image label, bounding box label, and scribble label
… propose a novel weakly-supervised salient object detection method using point supervision. … first design an adaptive masked flood filling algorithm to generate pseudo labels.
… develop a transformer-based point-supervised saliency detection model to produce the first round of saliency maps.
… propose a Non-Salient Suppression (NSS) method to optimize the erroneous saliency maps generated in the first round and leverage them for the second round of training.
… method outperforms … state-of-the-art methods trained with the stronger supervision and even surpass several fully supervised state-of-the-art models. …
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
