no code implementations • 16 Jan 2024 • Haoran Zhu, Chang Xu, Wen Yang, Ruixiang Zhang, Yan Zhang, Gui-Song Xia
In this study, we address the intricate issue of tiny object detection under noisy label supervision.
2 code implementations • 7 Feb 2023 • Haoran Zhu, Boyuan Chen, Carter Yang
Vision transformer (ViT) is an attention neural network architecture that is shown to be effective for computer vision tasks.
no code implementations • 8 Oct 2022 • Haoran Zhu, Maryam Majzoubi, Arihant Jain, Anna Choromanska
Our algorithm, which we call TAME (Task-Agnostic continual learning using Multiple Experts), automatically detects the shift in data distributions and switches between task expert networks in an online manner.
no code implementations • 26 Sep 2022 • Shihong Fang, Haoran Zhu, Devansh Bisla, Anna Choromanska, Satish Ravindran, Dongyin Ren, Ryan Wu
The core of our approach is the novel detect-then-segment method for raw radar signals.
no code implementations • 31 Oct 2021 • Qi Gao, Hongtao Lin, Han Tu, Haoran Zhu, Runjie Wei, Guoping Zhang, Xueming Shao
CC-FCN has two types of input layers, one is for the particle images, and the other is for the initial velocity field calculated using cross-correlation with a coarse resolution.
no code implementations • NeurIPS 2020 • Haoran Zhu, Pavankumar Murali, Dzung T. Phan, Lam M. Nguyen, Jayant R. Kalagnanam
Several recent publications report advances in training optimal decision trees (ODT) using mixed-integer programs (MIP), due to algorithmic advances in integer programming and a growing interest in addressing the inherent suboptimality of heuristic approaches such as CART.