1 code implementation • 29 Apr 2024 • Jun Yu, Yutong Dai, Xiaokang Liu, Jin Huang, Yishan Shen, Ke Zhang, Rong Zhou, Eashan Adhikarla, Wenxuan Ye, Yixin Liu, Zhaoming Kong, Kai Zhang, Yilong Yin, Vinod Namboodiri, Brian D. Davison, Jason H. Moore, Yong Chen
Overall, we hope this survey provides the research community with a comprehensive overview of the advancements in MTL from its inception in 1997 to the present in 2023.
1 code implementation • 12 Dec 2023 • Zhongyi Han, Guanglin Zhou, Rundong He, Jindong Wang, Tailin Wu, Yilong Yin, Salman Khan, Lina Yao, Tongliang Liu, Kun Zhang
We further investigate its adaptability to controlled data perturbations and examine the efficacy of in-context learning as a tool to enhance its adaptation.
1 code implementation • 11 Dec 2023 • Bingzheng Wang, Guoqiang Wu, Teng Pang, Yan Zhang, Yilong Yin
To address this issue, we propose a method named diffusion adversarial imitation learning (DiffAIL), which introduces the diffusion model into the AIL framework.
1 code implementation • 14 Jun 2023 • Ren Wang, Haoliang Sun, Qi Wei, Xiushan Nie, Yuling Ma, Yilong Yin
The key idea is to first break the rote memories by network pruning to address memorization overfitting in the inner loop, and then the gradients of pruned sub-networks naturally form the high-quality augmentation of the meta-gradient to alleviate learner overfitting in the outer loop.
no code implementations • 2 Jun 2023 • Qiangchang Wang, Yilong Yin
We hope that this survey can shed light on future research in the computer vision field.
1 code implementation • 9 May 2023 • Guoqiang Wu, Chongxuan Li, Yilong Yin
We theoretically identify a critical factor of the dataset affecting the generalization bounds: \emph{the label-wise class imbalance}.
no code implementations • CVPR 2023 • Ren Wang, Haoliang Sun, Yuling Ma, Xiaoming Xi, Yilong Yin
To overcome them, we propose a novel bi-level-optimization-based multi-view learning framework, where the representation is learned in a uniform-to-specific manner.
no code implementations • CVPR 2023 • Qi Wei, Lei Feng, Haoliang Sun, Ren Wang, Chenhui Guo, Yilong Yin
To this end, we propose a novel framework called stochastic noise-tolerated supervised contrastive learning (SNSCL) that confronts label noise by encouraging distinguishable representation.
no code implementations • CVPR 2023 • Fan Wang, Zhongyi Han, Zhiyan Zhang, Rundong He, Yilong Yin
Source free domain adaptation (SFDA) aims to transfer a trained source model to the unlabeled target domain without accessing the source data.
no code implementations • 16 Sep 2022 • Rundong He, Rongxue Li, Zhongyi Han, Yilong Yin
Based on limited ID labeled data and sufficient unlabeled data, we define a new setting called Weakly-Supervised Out-of-Distribution Detection (WSOOD).
1 code implementation • 24 Aug 2022 • Qi Wei, Haoliang Sun, Xiankai Lu, Yilong Yin
Sample selection is an effective strategy to mitigate the effect of label noise in robust learning.
3 code implementations • 12 Jun 2022 • Yuhang Dong, Gongping Yang, Yilong Yin
Besides, a plug-and-play Spatial Attention Block (SAB) is proposed to enhance features along with the spatial location information.
Ranked #1 on Heart rate estimation on VIPL-HR (using extra training data)
Heart rate estimation Photoplethysmography (PPG) heart rate estimation
no code implementations • 7 Jun 2022 • Ziqi Zhou, Li Lian, Yilong Yin, Ze Wang
Guided by that maximum rate, a novel and efficient hierarchical network pruning algorithm is developed to maximally condense the neuronal network structure without sacrificing network performance.
no code implementations • 22 May 2022 • Fan Wang, Zhongyi Han, Zhiyan Zhang, Yilong Yin
We then propose minimum happy points learning (MHPL) to actively explore and exploit MH points.
no code implementations • 22 Mar 2022 • Tiantian He, Zhibin Li, Yongshun Gong, Yazhou Yao, Xiushan Nie, Yilong Yin
Non-linear activation functions, e. g., Sigmoid, ReLU, and Tanh, have achieved great success in neural networks (NNs).
no code implementations • 18 Mar 2022 • Jin Huang, Lu Zhang, Yongshun Gong, Jian Zhang, Xiushan Nie, Yilong Yin
Series photo selection (SPS) is an important branch of the image aesthetics quality assessment, which focuses on finding the best one from a series of nearly identical photos.
no code implementations • 9 Mar 2022 • Lianxin Song, Xiaohui Han, Guangqi Liu, Wentong Wang, Chaoran Cui, Yilong Yin
SMAJudge utilizes two sequential components to model the complete proceeding from the lower court to the appellate court and employs an attention mechanism to make the prediction more explainable, which handles the challenges of AJP effectively.
no code implementations • CVPR 2022 • Rundong He, Zhongyi Han, Xiankai Lu, Yilong Yin
To take advantage of these unseen-class data and ensure performance, we propose a safe SSL method called SAFE-STUDENT from the teacher-student view.
no code implementations • CVPR 2022 • Fan Wang, Zhongyi Han, Yongshun Gong, Yilong Yin
In contrast, we provide a fascinating insight: rather than attempting to learn domain-invariant representations, it is better to explore the domain-invariant parameters of the source model.
no code implementations • CVPR 2022 • Zheyun Qin, Xiankai Lu, Xiushan Nie, Yilong Yin, Jianbing Shen
Video Instance Segmentation (VIS) needs to automatically track and segment multiple objects in videos that rely on modeling the spatial-temporal interactions of the instances.
1 code implementation • 8 Nov 2021 • Haoliang Sun, Chenhui Guo, Qi Wei, Zhongyi Han, Yilong Yin
In this paper, we propose warped probabilistic inference (WarPI) to achieve adaptively rectifying the training procedure for the classification network within the meta-learning scenario.
1 code implementation • 13 Aug 2021 • Zhongyi Han, Haoliang Sun, Yilong Yin
However, the learning processes of domain-invariant features and source hypothesis inevitably involve domain-specific information that would degrade the generalizability of UDA models on the target domain.
1 code implementation • 24 Jul 2021 • Qian Yu, Lei Qi, Luping Zhou, Lei Wang, Yilong Yin, Yinghuan Shi, Wuzhang Wang, Yang Gao
Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net.
1 code implementation • 22 Jul 2021 • Chaoran Cui, Jian Zong, Yuling Ma, Xinhua Wang, Lei Guo, Meng Chen, Yilong Yin
Academic performance prediction aims to leverage student-related information to predict their future academic outcomes, which is beneficial to numerous educational applications, such as personalized teaching and academic early warning.
1 code implementation • 22 Jul 2021 • Chaoran Cui, Xiaojie Li, Juan Du, Chunyun Zhang, Xiushan Nie, Meng Wang, Yilong Yin
Extensive experiments on real-world data demonstrate the effectiveness of our approach.
1 code implementation • 14 May 2021 • Haoliang Sun, Xiankai Lu, Haochen Wang, Yilong Yin, XianTong Zhen, Cees G. M. Snoek, Ling Shao
We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution.
no code implementations • 8 May 2021 • Yingjun Du, Haoliang Sun, XianTong Zhen, Jun Xu, Yilong Yin, Ling Shao, Cees G. M. Snoek
Specifically, we propose learning variational random features in a data-driven manner to obtain task-specific kernels by leveraging the shared knowledge provided by related tasks in a meta-learning setting.
no code implementations • 1 Apr 2021 • Xinfang Liu, Xiushan Nie, Zhifang Tan, Jie Guo, Yilong Yin
Natural language video localization (NLVL), which aims to locate a target moment from a video that semantically corresponds to a text query, is a novel and challenging task.
no code implementations • 23 Dec 2020 • Haoliang Sun, XianTong Zhen, Chris Bailey, Parham Rasoulinejad, Yilong Yin, Shuo Li
The Cobb angle that quantitatively evaluates the spinal curvature plays an important role in the scoliosis diagnosis and treatment.
1 code implementation • 7 Oct 2020 • Xiao Kang, Xingbo Liu, Xiushan Nie, Yilong Yin
With the development of medical imaging technology and machine learning, computer-assisted diagnosis which can provide impressive reference to pathologists, attracts extensive research interests.
no code implementations • 7 Oct 2020 • Xiao Kang, Xingbo Liu, Xiushan Nie, Xiaoming Xi, Yilong Yin
In this study, we propose a novel method named Attention Model Enhanced Network (AMEN), which is formulated in a multi-branch fashion with pixel-wised attention model and classification submodular.
1 code implementation • ICML 2020 • Xiantong Zhen, Haoliang Sun, Ying-Jun Du, Jun Xu, Yilong Yin, Ling Shao, Cees Snoek
We propose meta variational random features (MetaVRF) to learn adaptive kernels for the base-learner, which is developed in a latent variable model by treating the random feature basis as the latent variable.
no code implementations • 28 Apr 2020 • Zhongyi Han, Benzheng Wei, Yilong Yin, Shuo Li
In this paper, we propose the neural-symbolic learning (NSL) framework that performs human-like learning by unifying deep neural learning and symbolic logical reasoning for the spinal medical report generation.
1 code implementation • 27 Apr 2020 • Zhongyi Han, Xian-Jin Gui, Chaoran Cui, Yilong Yin
In non-stationary environments, learning machines usually confront the domain adaptation scenario where the data distribution does change over time.
no code implementations • 24 Apr 2020 • Xingbo Liu, Xiushan Nie, Qi Dai, Yupan Huang, Yilong Yin
Due to the compelling efficiency in retrieval and storage, similarity-preserving hashing has been widely applied to approximate nearest neighbor search in large-scale image retrieval.
no code implementations • arXiv:1909.01818 2019 • Xiaoli Liu, Jianqin Yin, Huaping Liu, Yilong Yin
Specifically, a skeletal representation is proposed by transforming the joint coordinate sequence into an image sequence, which can model the different correlations of different joints.
Ranked #1 on Pose Prediction on Filtered NTU RGB+D
no code implementations • 15 Mar 2019 • Xingbo Liu, Xiushan Nie, Yilong Yin
Label information is widely used in hashing methods because of its effectiveness of improving the precision.
1 code implementation • 1 Oct 2018 • Xingbo Liu, Xiushan Nie, Yilong Yin
In this paper, in contrast to existing hashing methods, we propose a novel generalized framework called fusion hashing (FH) to improve the precision of existing hashing methods without adding new constraints or penalty terms.
Data Structures and Algorithms Multimedia
no code implementations • CVPR 2017 • Haoliang Sun, Xian-Tong Zhen, Yuanjie Zheng, Gongping Yang, Yilong Yin, Shuo Li
Image-set classification has recently generated great popularity due to its widespread applications in computer vision.
no code implementations • 27 Jan 2016 • Xiushan Nie, Yilong Yin, Jiande Sun
Therefore, in the present study, we mine the assistance and consensus among different features based on tensor model, and present a new comprehensive feature to fully use them in the proposed video fingerprinting framework.