no code implementations • 12 Dec 2023 • Hu Zhang, Jianhua Xu, Tao Tang, Haiyang Sun, Xin Yu, Zi Huang, Kaicheng Yu
OpenSight utilizes 2D-3D geometric priors for the initial discernment and localization of generic objects, followed by a more specific semantic interpretation of the detected objects.
no code implementations • 6 Sep 2023 • Guang Yang, Yin Tang, Zhijian Wu, Jun Li, Jianhua Xu, Xili Wan
Recent mainstream masked distillation methods function by reconstructing selectively masked areas of a student network from the feature map of its teacher counterpart.
no code implementations • 4 Jun 2023 • Guangtao Wang, Jun Li, Jie Xie, Jianhua Xu, Bo Yang
In face detection, low-resolution faces, such as numerous small faces of a human group in a crowded scene, are common in dense face prediction tasks.
1 code implementation • 5 Apr 2023 • Binbin Feng, Jun Li, Jianhua Xu
To our knowledge, this is the first publicly available instance-level logo sketch dataset.
no code implementations • 23 Feb 2023 • Guangtao Wang, Jun Li, Zhijian Wu, Jianhua Xu, Jifeng Shen, Wankou Yang
Besides, this is conducive to estimating the locations of faces and enhancing the descriptive power of face features.
no code implementations • 31 Jan 2023 • Guang Yang, Yin Tang, Jun Li, Jianhua Xu, Xili Wan
As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart.