Výsledky vyhledávání - "Xu, Wenxiang"

Report

Deep Feature Response Discriminative Calibration

Autor: Xu, Wenxiang, Qiu, Tian, Zhou, Linyun, Feng, Zunlei, Song, Mingli, Wang, Huiqiong

Publikováno v: Neurocomputing 2025

Deep neural networks (DNNs) have numerous applications across various domains. Several optimization techniques, such as ResNet and SENet, have been proposed to improve model accuracy. These techniques improve the model performance by adjusting or cal

Externí odkaz: http://arxiv.org/abs/2411.13582

Zobrazit plný text záznamu

Report

Universal Hyperuniform Organization in Looped Leaf Vein Networks

Autor: Liu, Yuan, Chen, Duyu, Tian, Jianxiang, Xu, Wenxiang, Jiao, Yang

Leaf vein network is a hierarchical vascular system that transports water and nutrients to the leaf cells. The thick primary veins form a branched network, while the secondary veins develop closed circuits forming a well-defined cellular structure. T

Externí odkaz: http://arxiv.org/abs/2311.09551

Zobrazit plný text záznamu

Report

Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning

Autor: Xu, Wenxiang, Jing, Yongcheng, Zhou, Linyun, Huang, Wenqi, Cheng, Lechao, Feng, Zunlei, Song, Mingli

The problem of deep long-tailed learning, a prevalent challenge in the realm of generic visual recognition, persists in a multitude of real-world applications. To tackle the heavily-skewed dataset issue in long-tailed classification, prior efforts ha

Externí odkaz: http://arxiv.org/abs/2304.04135

Zobrazit plný text záznamu

Report

Team DETR: Guide Queries as a Professional Team in Detection Transformers

Autor: Qiu, Tian, Zhou, Linyun, Xu, Wenxiang, Cheng, Lechao, Feng, Zunlei, Song, Mingli

Recent proposed DETR variants have made tremendous progress in various scenarios due to their streamlined processes and remarkable performance. However, the learned queries usually explore the global context to generate the final set prediction, resu

Externí odkaz: http://arxiv.org/abs/2302.07116

Zobrazit plný text záznamu