Proxydet: Synthesizing proxy novel classes via classwise mixup for open-vocabulary object detection

J Jeong, G Park, J Yoo, H Jung, H Kim - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Open-vocabulary object detection (OVOD) aims to recognize novel objects whose
categories are not included in the training set. In order to classify these unseen classes …

Filter-pruning of lightweight face detectors using a geometric median criterion

K Gkrispanis, N Gkalelis… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Face detectors are becoming a crucial component of many applications, including
surveillance, that often have to run on edge devices with limited processing power and …

FDLite: A single stage lightweight face detector network

Y Aggarwal, P Guha - arxiv preprint arxiv:2406.19107, 2024 - arxiv.org
Face detection is frequently attempted by using heavy pre-trained backbone networks like
ResNet-50/101/152 and VGG16/19. Few recent works have also proposed lightweight …

Research on small-scale face detection methods in dense scenes

Y Cao, B Zhang, C Wang, M Wang - Applied Intelligence, 2025 - Springer
Face detection serves as the core foundation for applications such as face analysis,
recognition and reconstruction. In dense scenarios, the target scale difference is significant …

B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM Pruning

N Kaparinos, V Mezaris - arxiv preprint arxiv:2501.16917, 2025 - arxiv.org
Face detection is a computer vision application that increasingly demands lightweight
models to facilitate deployment on devices with limited computational resources. Neural …