no code implementations • 23 May 2024 • Yuanzhao Zhai, Zhuo Zhang, Kele Xu, Hanyang Peng, Yue Yu, Dawei Feng, Cheng Yang, Bo Ding, Huaimin Wang
To overcome this limitation, we propose Online Self-Preferring (OSP) language models to learn from self-generated response pairs and self-judged preference strengths.
no code implementations • 3 Dec 2021 • Hanyang Peng, Shiqi Yu
Specifically, the stricter the metric is, the more notable the gain is, improving \textbf{8. 2 mAP} on VOC2007 and \textbf{5. 4 mAP} on COCO2017 at metric $AP_{90}$.
4 code implementations • 3 Dec 2021 • Yuantao Feng, Shiqi Yu, Hanyang Peng, Yan-ran Li, JianGuo Zhang
However, with the tremendous increase in images and videos with variations in face scale, appearance, expression, occlusion and pose, traditional face detectors are challenged to detect various "in the wild" faces.
no code implementations • 25 Sep 2019 • Hanyang Peng, Shiqi Yu
Batch Normalization (BatchNorm) has been a default module in modern deep networks due to its effectiveness for accelerating training deep neural networks.
no code implementations • 2 Apr 2015 • Hanyang Peng, Yong Fan
In this paper, we propose a novel sparse learning based feature selection method that directly optimizes a large margin linear classification model sparsity with l_(2, p)-norm (0 < p < 1)subject to data-fitting constraints, rather than using the sparsity as a regularization term.