56 citations · 59 across the 7 of their papers we have counts for
7 papers
FACT: A Simple and Efficient Framework for Active Finetuning
Wenshuai Xu, You Song, Yuzhuo Cui +3
The main goal of active finetuning is to improve a pretrained model's performance on a specific task or domain by finetuning it with carefully selected informative or challenging d…
Generating High-quality Symbolic Music Using Fine-grained Discriminators
Zhedong Zhang, Liang Li, Jiehua Zhang +5
Existing symbolic music generation methods usually utilize discriminator to improve the quality of generated music via global perception of music. However, considering the complexi…
FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection
Zheng Jiang, Jinqing Zhang, Yanan Zhang +4
Although multi-view 3D object detection based on the Bird's-Eye-View (BEV) paradigm has garnered widespread attention as an economical and deployment-friendly perception solution f…
Quality-aware Selective Fusion Network for V-D-T Salient Object Detection
Liuxin Bao, Xiaofei Zhou, Xiankai Lu +5
Depth images and thermal images contain the spatial geometry information and surface temperature information, which can act as complementary information for the RGB modality. Howev…
YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images
Chenguang Liu, Guangshuai Gao, Ziyue Huang +3
Detecting objects from aerial images poses significant challenges due to the following factors: 1) Aerial images typically have very large sizes, generally with millions or even hu…
ActiveDC: Distribution Calibration for Active Finetuning
Wenshuai Xu, Zhenghui Hu, Yu Lu +3
The pretraining-finetuning paradigm has gained popularity in various computer vision tasks. In this paradigm, the emergence of active finetuning arises due to the abundance of larg…
Improving Multi-Person Pose Tracking with A Confidence Network
Zehua Fu, Wenhang Zuo, Zhenghui Hu +2
Human pose estimation and tracking are fundamental tasks for understanding human behaviors in videos. Existing top-down framework-based methods usually perform three-stage tasks: h…