Semi-Supervised Image Captioning Considering Wasserstein Graph Matching

arXiv:2403.17995v1 Announce Type: cross
Abstract: Image captioning can automatically generate captions for the given images, and the key challenge is to learn a mapping function from visual features to natural language features. Existing approaches are mostly supervised ones, i.e., each image has a corresponding sentence in the training set. However, considering that describing images always requires a huge of manpower, we usually have limited amount of described images (i.e., image-text pairs) and a large number of undescribed images in real-world …

abstract arxiv captioning captions challenge cs.ai cs.cv cs.lg features function generate graph however image images key language learn mapping natural natural language semi-supervised set the key training type visual