Zobrazeno 1 - 10
of 3 489
pro vyhledávání: '"Dong, Zhen"'
In this paper, we explore a novel framework, EGIInet (Explicitly Guided Information Interaction Network), a model for View-guided Point cloud Completion (ViPC) task, which aims to restore a complete point cloud from a partial one with a single view i
Externí odkaz:
http://arxiv.org/abs/2407.02887
Autor:
Yang, Huanrui, Huang, Yafeng, Dong, Zhen, Gudovskiy, Denis A, Okuno, Tomoyuki, Nakata, Yohei, Du, Yuan, Keutzer, Kurt, Zhang, Shanghang
The impact of quantization on the overall performance of deep learning models is a well-studied problem. However, understanding and mitigating its effects on a more fine-grained level is still lacking, especially for harder tasks such as object detec
Externí odkaz:
http://arxiv.org/abs/2407.03442
Autor:
Feng, Aosong, Qiu, Weikang, Bai, Jinbin, Zhang, Xiao, Dong, Zhen, Zhou, Kaicheng, Ying, Rex, Tassiulas, Leandros
Building on the success of text-to-image diffusion models (DPMs), image editing is an important application to enable human interaction with AI-generated content. Among various editing methods, editing within the prompt space gains more attention due
Externí odkaz:
http://arxiv.org/abs/2403.04880
Autor:
Zhou, Jiahao, Long, Chen, Xie, Yue, Wang, Jialiang, Li, Boheng, Wang, Haiping, Chen, Zhe, Dong, Zhen
Developing a unified multi-task foundation model has become a critical challenge in computer vision research. In the current field of 3D computer vision, most datasets only focus on single task, which complicates the concurrent training requirements
Externí odkaz:
http://arxiv.org/abs/2402.19059
Autor:
Yuan, Zhihang, Shang, Yuzhang, Zhou, Yang, Dong, Zhen, Zhou, Zhe, Xue, Chenhao, Wu, Bingzhe, Li, Zhikai, Gu, Qingyi, Lee, Yong Jae, Yan, Yan, Chen, Beidi, Sun, Guangyu, Keutzer, Kurt
The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is vibrant, there hasn't been a concise framework that analyzes the variou
Externí odkaz:
http://arxiv.org/abs/2402.16363
Autor:
Ma, Ze, Zhou, Daquan, Yeh, Chun-Hsiao, Wang, Xue-She, Li, Xiuyu, Yang, Huanrui, Dong, Zhen, Keutzer, Kurt, Feng, Jiashi
Creating content with specified identities (ID) has attracted significant interest in the field of generative models. In the field of text-to-image generation (T2I), subject-driven creation has achieved great progress with the identity controlled via
Externí odkaz:
http://arxiv.org/abs/2402.09368
Automated Aerial Triangulation (AAT), aiming to restore image pose and reconstruct sparse points simultaneously, plays a pivotal role in earth observation. With its rich research heritage spanning several decades in photogrammetry, AAT has evolved in
Externí odkaz:
http://arxiv.org/abs/2402.01134
Autor:
Ma, Rui, Zhou, Qiang, Jin, Yizhu, Zhou, Daquan, Xiao, Bangjun, Li, Xiuyu, Qu, Yi, Singh, Aishani, Keutzer, Kurt, Hu, Jingtong, Xie, Xiaodong, Dong, Zhen, Zhang, Shanghang, Zhou, Shiji
Copyright law confers upon creators the exclusive rights to reproduce, distribute, and monetize their creative works. However, recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement. These technologi
Externí odkaz:
http://arxiv.org/abs/2403.12052
Autor:
Zhang, Rongyu, Luo, Yulin, Liu, Jiaming, Yang, Huanrui, Dong, Zhen, Gudovskiy, Denis, Okuno, Tomoyuki, Nakata, Yohei, Keutzer, Kurt, Du, Yuan, Zhang, Shanghang
The Mixture-of-Experts (MoE) approach has demonstrated outstanding scalability in multi-task learning including low-level upstream tasks such as concurrent removal of multiple adverse weather effects. However, the conventional MoE architecture with p
Externí odkaz:
http://arxiv.org/abs/2312.16610
Autor:
Chen, Anthony, Yang, Huanrui, Gan, Yulu, Gudovskiy, Denis A, Dong, Zhen, Wang, Haofan, Okuno, Tomoyuki, Nakata, Yohei, Keutzer, Kurt, Zhang, Shanghang
Uncertainty estimation is crucial for machine learning models to detect out-of-distribution (OOD) inputs. However, the conventional discriminative deep learning classifiers produce uncalibrated closed-set predictions for OOD data. A more robust class
Externí odkaz:
http://arxiv.org/abs/2312.09148