Zobrazeno 1 - 10
of 208
pro vyhledávání: '"Feng Wenquan"'
Dataset Distillation (DD) is an emerging technique that compresses large-scale datasets into significantly smaller synthesized datasets while preserving high test performance and enabling the efficient training of large models. However, current resea
Externí odkaz:
http://arxiv.org/abs/2411.09265
Autor:
Zhou, Zheng, Zhao, Hongbo, Cheng, Guangliang, Li, Xiangtai, Lyu, Shuchang, Feng, Wenquan, Zhao, Qi
Dataset Distillation (DD) aims to distill knowledge from extensive datasets into more compact ones while preserving performance on the test set, thereby reducing storage costs and training expenses. However, existing methods often suffer from computa
Externí odkaz:
http://arxiv.org/abs/2406.01112
Autor:
Zhou, Zheng, Zhao, Hongbo, Liu, Ju, Zhang, Qiaosheng, Geng, Liwei, Lyu, Shuchang, Feng, Wenquan
Recent studies have shown that Adversarial Patches (APs) can effectively manipulate object detection models. However, the conspicuous patterns often associated with these patches tend to attract human attention, posing a significant challenge. Existi
Externí odkaz:
http://arxiv.org/abs/2312.17431
Autor:
Wang, Chunlei, Feng, Wenquan, Li, Xiangtai, Cheng, Guangliang, Lyu, Shuchang, Liu, Binghao, Chen, Lijiang, Zhao, Qi
Open-vocabulary learning has emerged as a cutting-edge research area, particularly in light of the widespread adoption of vision-based foundational models. Its primary objective is to comprehend novel concepts that are not encompassed within a predef
Externí odkaz:
http://arxiv.org/abs/2310.14374
Autor:
Li, Menghao, Wang, Chunlei, Feng, Wenquan, Lyu, Shuchang, Cheng, Guangliang, Li, Xiangtai, Liu, Binghao, Zhao, Qi
Visual Grounding (VG) aims at localizing target objects from an image based on given expressions and has made significant progress with the development of detection and vision transformer. However, existing VG methods tend to generate false-alarm obj
Externí odkaz:
http://arxiv.org/abs/2307.12392
Cell instance segmentation is a new and challenging task aiming at joint detection and segmentation of every cell in an image. Recently, many instance segmentation methods have applied in this task. Despite their great success, there still exists two
Externí odkaz:
http://arxiv.org/abs/2208.08078
Publikováno v:
In Applied Acoustics 15 February 2025 230
Autor:
Zhou, Xinjie, Chi, Shichun, Jia, Yufeng, Guo, Yu, Feng, Wenquan, Yan, Shihao, Wang, Tengteng, Ma, Xiyu
Publikováno v:
In Powder Technology 15 January 2025 449
Person re-identification (reID) aims at retrieving a person from images captured by different cameras. For deep-learning-based reID methods, it has been proved that using local features together with global feature could help to give robust represent
Externí odkaz:
http://arxiv.org/abs/2111.14411
Publikováno v:
In Chinese Journal of Aeronautics September 2024 37(9):328-346