Zobrazeno 1 - 10
of 70
pro vyhledávání: '"Zhai, Jiang"'
Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. This strict restriction enlarges the difficulty of alleviating catastrophic forgetting since all techniques can only b
Externí odkaz:
http://arxiv.org/abs/2312.12722
Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) as efficient learners for CIL. MAEs were originally designed to learn u
Externí odkaz:
http://arxiv.org/abs/2308.12510
Autor:
Zhai, Jiang-Tian, Feng, Ze, Du, Jinhao, Mao, Yongqiang, Liu, Jiang-Jiang, Tan, Zichang, Zhang, Yifu, Ye, Xiaoqing, Wang, Jingdong
Modern autonomous driving systems are typically divided into three main tasks: perception, prediction, and planning. The planning task involves predicting the trajectory of the ego vehicle based on inputs from both internal intention and the external
Externí odkaz:
http://arxiv.org/abs/2305.10430
Publikováno v:
Shuitu Baochi Xuebao, Vol 38, Iss 4, Pp 371-381 (2024)
[Objective] Current research mainly focuses on long-term frequency studies in non-karst areas, but there is insufficient research on hydrochemical sampling frequency under different rainfall levels in karst areas Inorder on determining the optimal sa
Externí odkaz:
https://doaj.org/article/ee8c0cb0d7594140b2ab47ff68734960
Publikováno v:
Meitan xuebao, Vol 49, Iss 7, Pp 3199-3215 (2024)
The research objectives are to reveal the eco-environmental quality of surface mining areas in semi-arid grasslands, separate the ecological cumulative effects of anthropogenic activities and examine their evolving trends. Based on the concept of eco
Externí odkaz:
https://doaj.org/article/7ce9101685484188a9459027be7db148
Exemplar-free Class Incremental Learning (EFCIL) aims to sequentially learn tasks with access only to data from the current one. EFCIL is of interest because it mitigates concerns about privacy and long-term storage of data, while at the same time al
Externí odkaz:
http://arxiv.org/abs/2212.08251
Autor:
Zhai, Jiang-Tian, Zhang, Qi, Wu, Tong, Chen, Xing-Yu, Liu, Jiang-Jiang, Ren, Bo, Cheng, Ming-Ming
Learning fine-grained interplay between vision and language allows to a more accurate understanding for VisionLanguage tasks. However, it remains challenging to extract key image regions according to the texts for semantic alignments. Most existing w
Externí odkaz:
http://arxiv.org/abs/2211.16208
Publikováno v:
In Pattern Recognition October 2024 154
Publikováno v:
In Journal of Visual Communication and Image Representation April 2024 100
Publikováno v:
Planta, 2020 Mar 01. 251(3), 1-19.
Externí odkaz:
https://www.jstor.org/stable/48742162