1Sun Yat-Sen University, 2University of Edinburgh
email@example.com, firstname.lastname@example.org, email@example.com
* Equal contribution.
✉ Corresponding author.
Important people detection is to automatically detect the individuals who play the most important roles in a social event image, which requires the designed model to understand a high-level pattern. However, existing methods rely heavily on supervised learning using large quantities of annotated image samples, which are more costly to collect for important people detection than for individual entity recognition (e.g., object recognition). To overcome this problem, we propose learning important people detection on partially annotated images. Our approach iteratively learns to assign pseudo-labels to individuals in un-annotated images and learns to update the important people detection model based on data with both labels and pseudo-labels. To alleviate the pseudo-labelling imbalance problem, we introduce a ranking strategy for pseudo-label estimation, and also introduce two weighting strategies: one for weighting the confidence that individuals are important people to strengthen the learning on important people and the other for neglecting noisy unlabelled images (i.e., images without any important people). We have collected two large-scale datasets for evaluation. The extensive experimental results clearly confirm the efficacy of our method attained by leveraging unlabelled images for improving the performance of important people detection.
▸ Code and datasets: The datasets are provided for academic use only, please contact Fa-Ting Hong or Wei-Hong Li. By downloading the dataset, you guarantee that you will use this dataset for academic work only. As we have a patent for the code, we are unable to release it.
Personally, I am quite fond of both the semi-supervised learning and important people detection topics (and some extension of both). If you are interested in both topics or you have any ideas, please feel free to discuss with me (Wei-Hong).