Most state-of-the-art synthetic aperture radar (SAR) ship detection methods based on deep
learning require large amounts of labeled data for network training. However, the annotation …

Object detection methods have achieved remarkable performances when the training and
testing data satisfy the assumption of iid However, the training and testing data may be …

In typical unsupervised domain adaptive object detection, it is assumed that extensive
unlabeled training data from the target domain can be easily obtained. However, in some …

In the context of intelligent driving, pedestrian detection faces challenges related to low
accuracy in target recognition and positioning. To address this issue, a pedestrian detection …

Existing works generally adopt the encoder-decoder structure for Multi-task Dense
Prediction, where the encoder extracts the task-generic features, and multiple decoders …

Autonomous vehicle scenarios often involve occluded and distant pedestrians, leading to
missed and false detections or models that are too large to deploy. To address these issues …