This paper deals with Semi-supervised Multi-label Learning (SSMLL) , which tries to train models when only a portion of the data has multiple labels.
The most prominent paper using this acronym is . BBAM.rar
It uses a trained object detector to find the "smallest area" of an image that makes the detector produce the same result, effectively creating a map that identifies the object within the box. BBAM.rar
Published at CVPR 2021 (Conference on Computer Vision and Pattern Recognition). BBAM.rar
This research focuses on Weakly Supervised Learning (WSL) , where the goal is to perform complex tasks like pixel-level segmentation using only simple bounding box labels rather than expensive pixel-by-pixel annotations.
Sometimes specialized datasets related to the papers above are shared this way.