Facilitating Semi-Supervised Pedestrian Detection with Structurally Controllable Instance Synthesis

The performance of pedestrian detectors typically relies on sufficient labeled data, and semi-supervised learning is a promising way to address the deficiency in manual annotations by utilizing sufficient unlabeled images. In this work, we design a Structure-Controllable Pedestrian Instance Generation approach (SCPIG), which is tailored to semi-supervised pedestrian detection. Specifically, we adopt a mask encoder to transform mask images into the embeddings encapsulating structure knowledge. In addition, we incorporate a mapping network to transform random latent code and a conditional generation network to synthesize diverse pedestrian instances, where the transformed code and mask embedding control pedestrian appearance and structure, respectively. The synthesized pedestrian instances are used to construct high-quality pseudo-labeled images for training pedestrian detectors. Extensive experiments validate the effectiveness of SCPIG in controllable pedestrian instance synthesizing and semi-supervised pedestrian detection.