Zobrazeno 1 - 10
of 449
pro vyhledávání: '"Dong, Bowen"'
We introduce LPT++, a comprehensive framework for long-tailed classification that combines parameter-efficient fine-tuning (PEFT) with a learnable model ensemble. LPT++ enhances frozen Vision Transformers (ViTs) through the integration of three core
Externí odkaz:
http://arxiv.org/abs/2409.11323
Autor:
Singer, Lennart, Dong, Bowen, Mohamed, M. A. A., Carstens, Frederik L., Hampel, Silke, Gräßler, Nico, Klingeler, Rüdiger
Lithium-rich antiperovskite promise to be a compelling high-capacity cathode material due to existence of both cationic and anionic redox activity. Little is however known about the effect of separating the electrochemical cationic from the anionic p
Externí odkaz:
http://arxiv.org/abs/2407.13631
Model Weight Averaging (MWA) is a technique that seeks to enhance model's performance by averaging the weights of multiple trained models. This paper first empirically finds that 1) the vanilla MWA can benefit the class-imbalanced learning, and 2) pe
Externí odkaz:
http://arxiv.org/abs/2404.16331
In this paper, we delve into the realm of vision transformers for continual semantic segmentation, a problem that has not been sufficiently explored in previous literature. Empirical investigations on the adaptation of existing frameworks to vanilla
Externí odkaz:
http://arxiv.org/abs/2402.16674
Autor:
Li, Lijun, Dong, Bowen, Wang, Ruohui, Hu, Xuhao, Zuo, Wangmeng, Lin, Dahua, Qiao, Yu, Shao, Jing
In the rapidly evolving landscape of Large Language Models (LLMs), ensuring robust safety measures is paramount. To meet this crucial need, we propose \emph{SALAD-Bench}, a safety benchmark specifically designed for evaluating LLMs, attack, and defen
Externí odkaz:
http://arxiv.org/abs/2402.05044
Autor:
Huang, Tianyu, Zeng, Yihan, Dong, Bowen, Xu, Hang, Xu, Songcen, Lau, Rynson W. H., Zuo, Wangmeng
Recent works learn 3D representation explicitly under text-3D guidance. However, limited text-3D data restricts the vocabulary scale and text control of generations. Generators may easily fall into a stereotype concept for certain text prompts, thus
Externí odkaz:
http://arxiv.org/abs/2309.17175
Autor:
Li, Zhenyu, Fan, Sunqi, Gu, Yu, Li, Xiuxing, Duan, Zhichao, Dong, Bowen, Liu, Ning, Wang, Jianyong
Knowledge base question answering (KBQA) is a critical yet challenging task due to the vast number of entities within knowledge bases and the diversity of natural language questions posed by users. Unfortunately, the performance of most KBQA models t
Externí odkaz:
http://arxiv.org/abs/2308.12060
Autor:
Wang, Zhuo, Li, Rongzhen, Dong, Bowen, Wang, Jie, Li, Xiuxing, Liu, Ning, Mao, Chenhui, Zhang, Wei, Dong, Liling, Gao, Jing, Wang, Jianyong
Recent investigations show that large language models (LLMs), specifically GPT-4, not only have remarkable capabilities in common Natural Language Processing (NLP) tasks but also exhibit human-level performance on various professional and academic be
Externí odkaz:
http://arxiv.org/abs/2306.01499
Existing open-world universal segmentation approaches usually leverage CLIP and pre-computed proposal masks to treat open-world segmentation tasks as proposal classification. However, 1) these works cannot handle universal segmentation in an end-to-e
Externí odkaz:
http://arxiv.org/abs/2303.06547
Prompt tuning has been employed as an efficient way to adapt large vision-language pre-trained models (e.g. CLIP) to various downstream tasks in data-limited or label-limited settings. Nonetheless, visual data (e.g., images) is by default prerequisit
Externí odkaz:
http://arxiv.org/abs/2211.12739