Search Results for author: Zihao Zhu

Found 22 papers, 8 papers with code

LoCI-DiffCom: Longitudinal Consistency-Informed Diffusion Model for 3D Infant Brain Image Completion

no code implementations17 May 2024 Zihao Zhu, Tianli Tao, Yitian Tao, Haowen Deng, Xinyi Cai, Gaofeng Wu, Kaidong Wang, Haifeng Tang, Lixuan Zhu, Zhuoyang Gu, Jiawei Huang, Dinggang Shen, Han Zhang

The infant brain undergoes rapid development in the first few years after birth. Compared to cross-sectional studies, longitudinal studies can depict the trajectories of infants brain development with higher accuracy, statistical power and flexibility. However, the collection of infant longitudinal magnetic resonance (MR) data suffers a notorious dropout problem, resulting in incomplete datasets with missing time points.

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning

no code implementations26 Jan 2024 Baoyuan Wu, Hongrui Chen, Mingda Zhang, Zihao Zhu, Shaokui Wei, Danni Yuan, Mingli Zhu, Ruotong Wang, Li Liu, Chao Shen

We hope that our efforts could build a solid foundation of backdoor learning to facilitate researchers to investigate existing algorithms, develop more innovative algorithms, and explore the intrinsic mechanism of backdoor learning.

Backdoor Attack

Enhanced Few-Shot Class-Incremental Learning via Ensemble Models

no code implementations14 Jan 2024 Mingli Zhu, Zihao Zhu, Sihong Chen, Chen Chen, Baoyuan Wu

To tackle overfitting challenge, we design a new ensemble model framework cooperated with data augmentation to boost generalization.

Data Augmentation Few-Shot Class-Incremental Learning +2

Defenses in Adversarial Machine Learning: A Survey

no code implementations13 Dec 2023 Baoyuan Wu, Shaokui Wei, Mingli Zhu, Meixi Zheng, Zihao Zhu, Mingda Zhang, Hongrui Chen, Danni Yuan, Li Liu, Qingshan Liu

Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsistent and incomprehensible predictions with humans at some particular cases.

C5: Towards Better Conversation Comprehension and Contextual Continuity for ChatGPT

no code implementations10 Aug 2023 Pan Liang, Danwei Ye, Zihao Zhu, Yunchao Wang, Wang Xia, Ronghua Liang, Guodao Sun

Large language models (LLMs), such as ChatGPT, have demonstrated outstanding performance in various fields, particularly in natural language understanding and generation tasks.

Natural Language Understanding

Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy

no code implementations14 Jul 2023 Zihao Zhu, Mingda Zhang, Shaokui Wei, Li Shen, Yanbo Fan, Baoyuan Wu

To further integrate it with normal training process, we then propose a learnable poisoning sample selection strategy to learn the mask together with the model parameters through a min-max optimization. Specifically, the outer loop aims to achieve the backdoor attack goal by minimizing the loss based on the selected samples, while the inner loop selects hard poisoning samples that impede this goal by maximizing the loss.

Backdoor Attack Data Poisoning

Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers

no code implementations1 Jun 2023 Ruotong Wang, Hongrui Chen, Zihao Zhu, Li Liu, Baoyuan Wu

Deep neural networks (DNNs) can be manipulated to exhibit specific behaviors when exposed to specific trigger patterns, without affecting their performance on benign samples, dubbed \textit{backdoor attack}.

Backdoor Attack backdoor defense +1

Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective

1 code implementation19 Feb 2023 Baoyuan Wu, Zihao Zhu, Li Liu, Qingshan Liu, Zhaofeng He, Siwei Lyu

Adversarial machine learning (AML) studies the adversarial phenomenon of machine learning, which may make inconsistent or unexpected predictions with humans.

Backdoor Attack

Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning

1 code implementation31 Oct 2022 Longkang Li, Siyuan Liang, Zihao Zhu, Chris Ding, Hongyuan Zha, Baoyuan Wu

Compared to the state-of-the-art reinforcement learning method, our model's network parameters are reduced to only 37\% of theirs, and the solution gap of our model towards the expert solutions decreases from 6. 8\% to 1. 3\% on average.

Computational Efficiency Imitation Learning +3

BackdoorBench: A Comprehensive Benchmark of Backdoor Learning

1 code implementation25 Jun 2022 Baoyuan Wu, Hongrui Chen, Mingda Zhang, Zihao Zhu, Shaokui Wei, Danni Yuan, Chao Shen

However, we find that the evaluations of new methods are often unthorough to verify their claims and accurate performance, mainly due to the rapid development, diverse settings, and the difficulties of implementation and reproducibility.

Backdoor Attack

From Shallow to Deep: Compositional Reasoning over Graphs for Visual Question Answering

no code implementations25 Jun 2022 Zihao Zhu

Meanwhile, the reasoning process should be explicit and explainable to understand the working mechanism of the model.

Question Answering Visual Question Answering +1

VAC2: Visual Analysis of Combined Causality in Event Sequences

no code implementations11 Jun 2022 Sujia Zhu, Yue Shen, Zihao Zhu, Wang Xia, Baofeng Chang, Ronghua Liang, Guodao Sun

To fill the absence of combined causes discovery on temporal event sequence data, eliminating and recruiting principles are defined to balance the effectiveness and controllability on cause combinations.

Causal Discovery Decision Making +2

BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis

2 code implementations10 Mar 2022 Haiyang Liu, Zihao Zhu, Naoya Iwamoto, Yichen Peng, Zhengqing Li, You Zhou, Elif Bozkurt, Bo Zheng

Achieving realistic, vivid, and human-like synthesized conversational gestures conditioned on multi-modal data is still an unsolved problem due to the lack of available datasets, models and standard evaluation metrics.

Gesture Generation Gesture Recognition

MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension

no code implementations8 Mar 2021 Wei Peng, Yue Hu, Jing Yu, Luxi Xing, Yuqiang Xie, Zihao Zhu, Yajing Sun

Most of the existing systems design a simple classifier to determine answerability implicitly without explicitly modeling mutual interaction and relation between the question and passage, leading to the poor performance for determining the unanswerable questions.

Machine Reading Comprehension Question Answering +2

Cross-modal Knowledge Reasoning for Knowledge-based Visual Question Answering

no code implementations31 Aug 2020 Jing Yu, Zihao Zhu, Yujing Wang, Weifeng Zhang, Yue Hu, Jianlong Tan

Finally, we perform graph neural networks to infer the global-optimal answer by jointly considering all the concepts.

Knowledge Graphs Question Answering +1

DAM: Deliberation, Abandon and Memory Networks for Generating Detailed and Non-repetitive Responses in Visual Dialogue

4 code implementations7 Jul 2020 Xiaoze Jiang, Jing Yu, Yajing Sun, Zengchang Qin, Zihao Zhu, Yue Hu, Qi Wu

The ability of generating detailed and non-repetitive responses is crucial for the agent to achieve human-like conversation.

Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering

no code implementations16 Jun 2020 Zihao Zhu, Jing Yu, Yujing Wang, Yajing Sun, Yue Hu, Qi Wu

In this paper, we depict an image by a multi-modal heterogeneous graph, which contains multiple layers of information corresponding to the visual, semantic and factual features.

Question Answering Visual Question Answering

Measuring Patient Similarities via a Deep Architecture with Medical Concept Embedding

1 code implementation9 Feb 2019 Zihao Zhu, Changchang Yin, Buyue Qian, Yu Cheng, Jishang Wei, Fei Wang

One major carrier for conducting patient similarity research is Electronic Health Records(EHRs), which are usually heterogeneous, longitudinal, and sparse.

Cannot find the paper you are looking for? You can Submit a new open access paper.