1 code implementation • 11 Apr 2024 • Lifan Jiang, Zhihui Wang, Changmiao Wang, Ming Li, Jiaxu Leng, Xindong Wu
In the present study, we introduce a novel framework designed to articulate object detection as a denoising diffusion process, which operates on the perturbed bounding boxes of annotated entities.
no code implementations • 14 Nov 2023 • Ziqiang Li, Chaoyue Wang, Xue Rui, Chao Xue, Jiaxu Leng, Bin Li
Few-shot image generation aims to train generative models using a small number of training images.
no code implementations • 27 Oct 2023 • Shuang Li, Jiaxu Leng, Ji Gan, Mengjingcheng Mo, Xinbo Gao
One pertains to the dependence on auxiliary models for shape feature extraction in the inference phase, along with the errors in generated infrared shapes due to the intrinsic modality disparity.
no code implementations • 24 Oct 2023 • Feng Gao, Jiaxu Leng, Ji Gan, Xinbo Gao
Moreover, to train the rank prediction head better, we propose Soft Gradient L1 Loss.
no code implementations • 18 Jul 2023 • Lin Yuan, Kai Liang, Xiao Pu, Yan Zhang, Jiaxu Leng, Tao Wu, Nannan Wang, Xinbo Gao
This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single lightweight framework.
no code implementations • 18 May 2023 • Feng Gao, Jiaxu Leng, Gan Ji, Xinbo Gao
However, in crowded pedestrian detection, the performance of DETRs is still unsatisfactory due to the inappropriate sample selection method which results in more false positives.
1 code implementation • 28 Oct 2022 • Yan Zhang, Xiyuan Gao, Qingyan Duan, Jiaxu Leng, Xiao Pu, Xinbo Gao
By stacking various layers of CSA blocks, we propose the Fourier Complex Transformer (FCT) model to learn global contextual information from VHR aerial images following the hierarchical manners.