no code implementations • ECCV 2020 • Jian Hu, Hongya Tuo, Chao Wang, Lingfeng Qiao, Haowen Zhong, Junchi Yan, Zhongliang Jing, Henry Leung
Previous methods typically match the whole source domain to target domain, which causes negative transfer due to the source-negative classes in source domain that does not exist in target domain.
1 code implementation • 12 Dec 2023 • Jian Hu, Jiayi Lin, Weitong Cai, Shaogang Gong
In this work, we aim to eliminate the need for manual prompt.
Camouflaged Object Segmentation with a Single Task-generic Prompt object-detection +2
2 code implementations • 23 Aug 2023 • Jian Hu, Li Tao, June Yang, Chandler Zhou
Learning from human preferences is crucial for language models (LMs) to effectively cater to human needs and societal values.
1 code implementation • 18 Jul 2023 • Wenyu Zhang, Qing Ding, Jian Hu, Yi Ma, Mingzhe Lu
Based on these two modules, we consulted the ResNet and design a pixel-wise graph attention network (PGANet).
no code implementations • 1 Jul 2023 • Yan Wang, Yuhang Li, Ruihao Gong, Aishan Liu, Yanfei Wang, Jian Hu, Yongqiang Yao, Yunchen Zhang, Tianzi Xiao, Fengwei Yu, Xianglong Liu
Extensive studies have shown that deep learning models are vulnerable to adversarial and natural noises, yet little is known about model robustness on noises caused by different system implementations.
1 code implementation • 2 Jun 2022 • Jian Hu, Haowen Zhong, Junchi Yan, Shaogang Gong, Guile Wu, Fei Yang
However, due to the significant imbalance between the amount of annotated data in the source and target domains, usually only the target distribution is aligned to the source domain, leading to adapting unnecessary source specific knowledge to the target domain, i. e., biased domain adaptation.
no code implementations • 23 May 2022 • Qilei Li, Jiabo Huang, Jian Hu, Shaogang Gong
In this work, we propose a Feature-Distribution Perturbation and Calibration (PECA) method to derive generic feature representations for person ReID, which is not only discriminative across cameras but also agnostic and deployable to arbitrary unseen target domains.
no code implementations • 26 Nov 2021 • Junquan Deng, Wei Shi, Jian Hu, Xianlong Jiao
We consider the mobile localization problem in future millimeter-wave wireless networks with distributed Base Stations (BSs) based on multi-antenna channel state information (CSI).
no code implementations • 29 Sep 2021 • Jian Hu, Siyang Jiang, Seth Austin Harding, Haibin Wu, Shih-wei Liao
QMIX, a popular MARL algorithm based on the monotonicity constraint, has been used as a baseline for the benchmark environments, such as Starcraft Multi-Agent Challenge (SMAC), Predator-Prey (PP).
no code implementations • 18 Sep 2021 • Jian Hu, Hongya Tuo, Shizhao Zhang, Chao Wang, Haowen Zhong, Zhikang Zou, Zhongliang Jing, Henry Leung, Ruping Zou
Partial Domain adaptation (PDA) aims to solve a more practical cross-domain learning problem that assumes target label space is a subset of source label space.
no code implementations • 26 Jun 2021 • Shizhao Zhang, Hongya Tuo, Jian Hu, Zhongliang Jing
Multi-scale instance level features alignment is presented to reduce instance domain shift effectively , such as variations in object appearance and viewpoint.
2 code implementations • 6 Feb 2021 • Jian Hu, Siyang Jiang, Seth Austin Harding, Haibin Wu, Shih-wei Liao
Multi-Agent Reinforcement Learning (MARL) has seen revolutionary breakthroughs with its successful application to multi-agent cooperative tasks such as computer games and robot swarms.
no code implementations • 6 Dec 2020 • Wei Wang, Xiaofu Xiong, Yufei He, Jian Hu, Hongzhou Chen
Mobile energy resources (MERs) have been shown to boost DS resilience effectively in recent years.
no code implementations • 9 Sep 2020 • Jian Hu, Seth Austin Harding, Haibin Wu, Siyue Hu, Shih-wei Liao
Existing methods such as Value Decomposition Network (VDN) and QMIX estimate the value of long-term returns as a scalar that does not contain the information of randomness.
no code implementations • 21 Jan 2020 • Youming Lei, Jian Hu, Jianpeng Ding
The numerical results show that the proposed method can effectively avoid the rapid divergence of the multi-layer LSTM model when reconstructing chaotic attractors, and demonstrate the feasibility of the combination of deep learning based on the gradient descent method and the empirical model.
no code implementations • 15 Oct 2018 • Xuanda Chen, Ziyu Xiong, Jian Hu
Vocal aging, a universal process of human aging, can largely affect one's language use, possibly including some subtle acoustic features of one's utterances like Voice Onset Time.