Deep learning breakthrough stimulates new research trends in civil infrastructure inspection,
whereas the lack of quality-guaranteed, human-annotated, free-of-charge, and publicly …

We analyze the DETR-based framework on semi-supervised object detection (SSOD) and
observe that (1) the one-to-one assignment strategy generates incorrect matching when the …

Self-training approaches recently achieved promising results in cross-domain object
detection, where people iteratively generate pseudo labels for unlabeled target domain …

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 …

Abstract Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for
boosting object detectors, has become an active task in recent years. However, existing …

Despite the prominent success of general object detection, the performance and efficiency of
Small Object Detection (SOD) are still unsatisfactory. Unlike existing works that struggle to …

Abstract With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage
detectors generally obtain limited promotions compared with two-stage clusters. We …

Semi-Supervised Object Detection (SSOD) has been successful in improving the
performance of both R-CNN series and anchor-free detectors. However, one-stage anchor …

Semi-supervised object detection is crucial for 3D scene understanding, efficiently
addressing the limitation of acquiring large-scale 3D bounding box annotations. Existing …

Scale variation across object instances is one of the key challenges in object detection.
Although modern detection models have achieved remarkable progress in dealing with the …