no code implementations • 1 Apr 2024 • Chenxi Shi, Penghao Liang, Yichao Wu, Tong Zhan, Zhengyu Jin
The integration of LLMOps into personalized recommendation systems marks a significant advancement in managing LLM-driven applications.
no code implementations • 15 Mar 2024 • Bo Song, Yuanhao Xu, Yichao Wu
Machine learning models have achieved significant milestones in various domains, for example, computer vision models have an exceptional result in object recognition, and in natural language processing, where Large Language Models (LLM) like GPT can start a conversation with human-like proficiency.
no code implementations • 13 Mar 2024 • Yichao Wu, Zhengyu Jin, Chenxi Shi, Penghao Liang, Tong Zhan
This paper explores the application of deep learning techniques, particularly focusing on BERT models, in sentiment analysis.
no code implementations • 5 Mar 2024 • Xiaonan Xu, Yichao Wu, Penghao Liang, Yuhang He, Han Wang
With the boom of e-commerce and web applications, recommender systems have become an important part of our daily lives, providing personalized recommendations based on the user's preferences.
no code implementations • 28 Feb 2024 • Yichao Wu, Yafei Xiang, Shuning Huo, Yulu Gong, Penghao Liang
In addressing the computational and memory demands of fine-tuning Large Language Models(LLMs), we propose LoRA-SP(Streamlined Partial Parameter Adaptation), a novel approach utilizing randomized half-selective parameter freezing within the Low-Rank Adaptation(LoRA)framework.
1 code implementation • 2 Aug 2023 • Jun Guo, Aishan Liu, Xingyu Zheng, Siyuan Liang, Yisong Xiao, Yichao Wu, Xianglong Liu
However, these defenses are now suffering problems of high inference computational overheads and unfavorable trade-offs between benign accuracy and stealing robustness, which challenges the feasibility of deployed models in practice.
2 code implementations • 16 May 2023 • Qinghong Sun, Zhenfei Yin, Yichao Wu, Yuanhan Zhang, Jing Shao
In this work, we propose a unified framework called Latent Distribution Adjusting (LDA) with properties of latent, discriminative, adaptive, generic to improve the robustness of the FAS model by adjusting complex data distribution with multiple prototypes.
no code implementations • 6 May 2023 • Ruijia Wu, Yuhang Wang, Huafeng Shi, Zhipeng Yu, Yichao Wu, Ding Liang
In this paper, we propose the Adversarial Decoupling Augmentation Framework (ADAF), addressing these issues by targeting the image-text fusion module to enhance the defensive performance of facial privacy protection algorithms.
no code implementations • ICCV 2023 • Zhipeng Yu, Jiaheng Liu, Haoyu Qin, Yichao Wu, Kun Hu, Jiayi Tian, Ding Liang
Knowledge distillation is an effective model compression method to improve the performance of a lightweight student model by transferring the knowledge of a well-performed teacher model, which has been widely adopted in many computer vision tasks, including face recognition (FR).
no code implementations • 15 Sep 2022 • ChunYu Sun, Chenye Xu, Chengyuan Yao, Siyuan Liang, Yichao Wu, Ding Liang, Xianglong Liu, Aishan Liu
Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, known as the robust fairness problem.
no code implementations • 12 Sep 2022 • Yuhang Wang, Huafeng Shi, Rui Min, Ruijia Wu, Siyuan Liang, Yichao Wu, Ding Liang, Aishan Liu
Most detection methods are designed to verify whether a model is infected with presumed types of backdoor attacks, yet the adversary is likely to generate diverse backdoor attacks in practice that are unforeseen to defenders, which challenge current detection strategies.
1 code implementation • 12 Jul 2022 • Gang Li, Xiang Li, Yujie Wang, Yichao Wu, Ding Liang, Shanshan Zhang
Specifically, we propose the Inverse NMS Clustering (INC) and Rank Matching (RM) to instantiate the dense supervision, without the widely used, conventional sparse pseudo labels.
no code implementations • 27 Apr 2022 • Yuanhan Zhang, Yichao Wu, Zhenfei Yin, Jing Shao, Ziwei Liu
In this work, we attempt to fill this gap by automatically addressing the noise problem from both label and data perspectives in a probabilistic manner.
no code implementations • 12 Apr 2022 • Jiaheng Liu, Haoyu Qin, Yichao Wu, Jinyang Guo, Ding Liang, Ke Xu
In this work, we observe that mutual relation knowledge between samples is also important to improve the discriminative ability of the learned representation of the student model, and propose an effective face recognition distillation method called CoupleFace by additionally introducing the Mutual Relation Distillation (MRD) into existing distillation framework.
1 code implementation • 30 Mar 2022 • Gang Li, Xiang Li, Yujie Wang, Yichao Wu, Ding Liang, Shanshan Zhang
Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which also plays an important role in ensuring the scale invariance.
no code implementations • 9 Dec 2021 • Gang Li, Xiang Li, Yujie Wang, Shanshan Zhang, Yichao Wu, Ding Liang
Based on the two observations, we propose Rank Mimicking (RM) and Prediction-guided Feature Imitation (PFI) for distilling one-stage detectors, respectively.
no code implementations • 24 Nov 2021 • Yujie Wang, Junqin Huang, Mengya Gao, Yichao Wu, Zhenfei Yin, Ding Liang, Junjie Yan
Transferring with few data in a general way to thousands of downstream tasks is becoming a trend of the foundation model's application.
no code implementations • 16 Nov 2021 • Jing Shao, Siyu Chen, Yangguang Li, Kun Wang, Zhenfei Yin, Yinan He, Jianing Teng, Qinghong Sun, Mengya Gao, Jihao Liu, Gengshi Huang, Guanglu Song, Yichao Wu, Yuming Huang, Fenggang Liu, Huan Peng, Shuo Qin, Chengyu Wang, Yujie Wang, Conghui He, Ding Liang, Yu Liu, Fengwei Yu, Junjie Yan, Dahua Lin, Xiaogang Wang, Yu Qiao
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society.
no code implementations • 2 Mar 2021 • Jiaheng Liu, Yudong Wu, Yichao Wu, Zhenmao Li, Chen Ken, Ding Liang, Junjie Yan
In this study, we make a key observation that the local con-text represented by the similarities between the instance and its inter-class neighbors1plays an important role forFR.
no code implementations • ICCV 2021 • Jiaheng Liu, Yudong Wu, Yichao Wu, Chuming Li, Xiaolin Hu, Ding Liang, Mengyu Wang
To estimate the LID of each face image in the verification process, we propose two types of LID Estimation (LIDE) methods, which are reference-based and learning-based estimation methods, respectively.
no code implementations • 27 May 2019 • Zhenmao Li, Yichao Wu, Ken Chen, Yudong Wu, Shunfeng Zhou, Jiaheng Liu, Junjie Yan
Example weighting algorithm is an effective solution to the training bias problem, however, most previous typical methods are usually limited to human knowledge and require laborious tuning of hyperparameters.