Previous pseudo-label approaches for semi-supervised object detection typically follow a
multi-stage schema, with the first stage to train an initial detector on a few labeled data …

Semi-supervised learning (SSL) has a potential to improve the predictive performance of
machine learning models using unlabeled data. Although there has been remarkable recent …

Supervised learning based object detection frameworks demand plenty of laborious manual
annotations, which may not be practical in real applications. Semi-supervised object …

Astounding performance of Transformers in natural language processing (NLP) has
delighted researchers to explore their utilization in computer vision tasks. Like other …

In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised
object detection (SSOD). Our core observation is that the oscillating pseudo-targets …

Object detection via inaccurate bounding box supervision has boosted a broad interest due
to the expensive high-quality annotation data or the occasional inevitability of low annotation …

The fast development of self-supervised learning (SSL) lowers the bar learning feature
representation from massive unlabeled data and has triggered a series of researches on …

摘要在人工智能迅速发展的今天, 深度神经网络广泛应用于各个研究领域并取得了巨大的成功,
但也同样面临着诸多挑战. 首先, 为了解决复杂的问题和提高模型的训练效果 …

Object detectors trained with weak annotations are affordable alternatives to fully-supervised
counterparts. However, there is still a significant performance gap between them. We …

Accurate player and ball detection has become increasingly important in recent years for
sport analytics. As most state-of-the-art methods rely on training deep learning networks in a …