4 papers
SD2AIL: Adversarial Imitation Learning from Synthetic Demonstrations via Diffusion Models
Pengcheng Li, Qiang Fang, Tong Zhao +2
Adversarial Imitation Learning (AIL) is a dominant framework in imitation learning that infers rewards from expert demonstrations to guide policy optimization. Although providing m…
Similarity Distance-Based Label Assignment for Tiny Object Detection
Shuohao Shi, Qiang Fang, Tong Zhao +1
Tiny object detection is becoming one of the most challenging tasks in computer vision because of the limited object size and lack of information. The label assignment strategy is…
Continual Learning through Networks Splitting and Merging with Dreaming-Meta-Weighted Model Fusion
Yi Sun, Xin Xu, Jian Li +3
It's challenging to balance the networks stability and plasticity in continual learning scenarios, considering stability suffers from the update of model and plasticity benefits fr…
Density-Guided Dense Pseudo Label Selection For Semi-supervised Oriented Object Detection
Tong Zhao, Qiang Fang, Shuohao Shi +1
Recently, dense pseudo-label, which directly selects pseudo labels from the original output of the teacher model without any complicated post-processing steps, has received conside…