For years, the YOLO series has been the de facto industry-level standard for efficient object
detection. The YOLO community has prospered overwhelmingly to enrich its use in a …

Abstract Knowledge distillation has been applied to various tasks successfully. The current
distillation algorithm usually improves students' performance by imitating the output of the …

The representation gap between teacher and student is an emerging topic in knowledge
distillation (KD). To reduce the gap and improve the performance, current methods often …

To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-
boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this …

Practical applications ask for object detection models that achieve high performance at low
overhead. Knowledge distillation demonstrates favorable potential in this case by …

Abstract Knowledge distillation (KD) is a widely-used technique to train compact models in
object detection. However, there is still a lack of study on how to distill between …

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 …

Open-vocabulary object detection aims to provide object detectors trained on a fixed set of
object categories with the generalizability to detect objects described by arbitrary text …

Abstract Large vision Transformers (ViTs) driven by self-supervised pre-training
mechanisms achieved unprecedented progress. Lightweight ViT models limited by the …

Previous knowledge distillation (KD) methods for object detection mostly focus on feature
imitation instead of mimicking the prediction logits due to its inefficiency in distilling the …