no code implementations • ICML 2020 • Mingjie Li, Lingshen He, Zhouchen Lin
By viewing ResNet as an explicit Euler discretization of an ordinary differential equation (ODE), for the first time, we find that the adversarial robustness of ResNet is connected to the numerical stability of the corresponding dynamic system.
no code implementations • 27 Feb 2024 • Yu Ran, Ao-Xiang Zhang, Mingjie Li, Weixuan Tang, Yuan-Gen Wang
Specifically, we first formulate the attack problem as maximizing the deviation between the estimated quality scores of original and perturbed images, while restricting the perturbed image distortions for visual quality preservation.
no code implementations • 15 Jan 2024 • Mingjie Li, Karin Verspoor
Information extraction techniques, including named entity recognition (NER) and relation extraction (RE), are crucial in many domains to support making sense of vast amounts of unstructured text data by identifying and connecting relevant information.
1 code implementation • NeurIPS 2023 • Yuetian Weng, Mingfei Han, Haoyu He, Mingjie Li, Lina Yao, Xiaojun Chang, Bohan Zhuang
By reusing predictions from key frames, we circumvent the need to process a large volume of video frames individually with resource-intensive segmentors, alleviating temporal redundancy and significantly reducing computational costs.
no code implementations • 15 Oct 2023 • Huilin Zhou, Huijie Tang, Mingjie Li, Hao Zhang, Zhenyu Liu, Quanshi Zhang
The AI model has surpassed human players in the game of Go, and it is widely believed that the AI model has encoded new knowledge about the Go game beyond human players.
no code implementations • 27 Apr 2023 • Meenakshi S. Kagda, Bonita Lam, Casey Litton, Corinn Small, Cricket A. Sloan, Emma Spragins, Forrest Tanaka, Ian Whaling, Idan Gabdank, Ingrid Youngworth, J. Seth Strattan, Jason Hilton, Jennifer Jou, Jessica Au, Jin-Wook Lee, Kalina Andreeva, Khine Lin, Matt Simison, Otto Jolanki, Philip Adenekan, Eric Douglas, Mingjie Li, Pedro Assis, Keenan Graham, Paul Sud, Stuart Miyasato, Weiwei Zhong, Yunhai Luo, Zachary Myers, J. Michael Cherry, Benjamin C. Hitz
Spanning two decades, the Encyclopaedia of DNA Elements (ENCODE) is a collaborative research project that aims to identify all the functional elements in the human and mouse genomes.
1 code implementation • 26 Apr 2023 • Bingqian Lin, Zicong Chen, Mingjie Li, Haokun Lin, Hang Xu, Yi Zhu, Jianzhuang Liu, Wenjia Cai, Lei Yang, Shen Zhao, Chenfei Wu, Ling Chen, Xiaojun Chang, Yi Yang, Lei Xing, Xiaodan Liang
In MOTOR, we combine two kinds of basic medical knowledge, i. e., general and specific knowledge, in a complementary manner to boost the general pretraining process.
1 code implementation • 26 Apr 2023 • Mingjie Li, Quanshi Zhang
For faithfulness, we prove the uniqueness of the AND (OR) interaction in quantifying the effect of the AND (OR) relationship between input variables.
1 code implementation • 24 Apr 2023 • Mingjie Li, Tharindu Rathnayake, Ben Beck, Lingheng Meng, Zijue Chen, Akansel Cosgun, Xiaojun Chang, Dana Kulić
Instance-level detection aims to detect which vehicle in the scene gives rise to a close pass near miss.
no code implementations • 3 Apr 2023 • Wen Shen, Lei Cheng, Yuxiao Yang, Mingjie Li, Quanshi Zhang
In this paper, we explain the inference logic of large language models (LLMs) as a set of symbolic concepts.
1 code implementation • CVPR 2023 • Mingjie Li, Bingqian Lin, Zicong Chen, Haokun Lin, Xiaodan Liang, Xiaojun Chang
To address the limitation, we propose a knowledge graph with Dynamic structure and nodes to facilitate medical report generation with Contrastive Learning, named DCL.
1 code implementation • 25 Feb 2023 • Mingjie Li, Quanshi Zhang
Recently, a series of studies have tried to extract interactions between input variables modeled by a DNN and define such interactions as concepts encoded by the DNN.
2 code implementations • 16 Jul 2022 • Mingjie Li, Rui Liu, Guangsi Shi, Mingfei Han, Changling Li, Lina Yao, Xiaojun Chang, Ling Chen
To further enhance forecasting accuracy, we introduce a memory-driven decoder.
1 code implementation • 13 Jun 2022 • Mingjie Li, Zeyan Li, Kanglin Yin, Xiaohui Nie, Wenchi Zhang, Kaixin Sui, Dan Pei
Fault diagnosis is critical in many domains, as faults may lead to safety threats or economic losses.
no code implementations • CVPR 2022 • Mingjie Li, Wenjia Cai, Karin Verspoor, Shirui Pan, Xiaodan Liang, Xiaojun Chang
To endow models with the capability of incorporating expert knowledge, we propose a Cross-modal clinical Graph Transformer (CGT) for ophthalmic report generation (ORG), in which clinical relation triples are injected into the visual features as prior knowledge to drive the decoding procedure.
no code implementations • 26 May 2022 • Mingjie Li, Hao Kong, Zhouchen Lin
Furthermore, we analyze the constraints of the inversion layer to ensure the output stability of the network to a certain extent.
1 code implementation • 4 May 2022 • Jie Ren, Mingjie Li, Meng Zhou, Shih-Han Chan, Quanshi Zhang
Based on the proposed metrics, we analyze two typical phenomena of the change of the transformation complexity during the training process, and explore the ceiling of a DNN's complexity.
1 code implementation • CVPR 2023 • Jie Ren, Mingjie Li, Qirui Chen, Huiqi Deng, Quanshi Zhang
This paper aims to illustrate the concept-emerging phenomenon in a trained DNN.
no code implementations • NeurIPS 2021 • Mingjie Li, Shaobo Wang, Quanshi Zhang
This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN.
no code implementations • 3 Nov 2021 • Ke Sun, Mingjie Li, Zhouchen Lin
In this paper, we endeavor to design strategies to achieve universal adversarial robustness.
no code implementations • 25 Oct 2021 • Mingjie Li, Hanzhou Wu, Xinpeng Zhang
Adversarial example generation has been a hot spot in recent years because it can cause deep neural networks (DNNs) to misclassify the generated adversarial examples, which reveals the vulnerability of DNNs, motivating us to find good solutions to improve the robustness of DNN models.
no code implementations • ICLR 2022 • Mingjie Li, Yisen Wang, Xingyu Xie, Zhouchen Lin
Works have shown the strong connections between some implicit models and optimization problems.
1 code implementation • Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) 2021 • Mingjie Li, Wenjia Cai, Rui Liu, Yuetian Weng, Xiaoyun Zhao, Cong Wang, Xin Chen, Zhong Liu, Caineng Pan, Mengke Li, Yizhi Liu, Flora D Salim, Karin Verspoor, Xiaodan Liang, Xiaojun Chang
Researchers have explored advanced methods from computer vision and natural language processing to incorporate medical domain knowledge for the generation of readable medical reports.
no code implementations • 1 Jan 2021 • Jie Ren, Mingjie Li, Meng Zhou, Shih-Han Chan, Zexu Liu, Quanshi Zhang
Based on the proposed metrics, we analyze two typical phenomena of the change of the transformation complexity during the training process, and explore the ceiling of a DNN’s complexity.
no code implementations • ICLR 2021 • Hao Zhang, Sen Li, Yinchao Ma, Mingjie Li, Yichen Xie, Quanshi Zhang
Experimental results on various DNNs and datasets have shown that the interaction loss can effectively improve the utility of dropout and boost the performance of DNNs.
no code implementations • 1 Jan 2021 • Jie Ren, Mingjie Li, Zexu Liu, Quanshi Zhang
This paper aims to define, visualize, and analyze the feature complexity that is learned by a DNN.
no code implementations • 24 Sep 2020 • Hao Zhang, Sen Li, Yinchao Ma, Mingjie Li, Yichen Xie, Quanshi Zhang
This paper aims to understand and improve the utility of the dropout operation from the perspective of game-theoretic interactions.
1 code implementation • 29 Jun 2020 • Jie Ren, Mingjie Li, Zexu Liu, Quanshi Zhang
This paper aims to define, quantify, and analyze the feature complexity that is learned by a DNN.
2 code implementations • 6 Jun 2020 • Mingjie Li, Fuyu Wang, Xiaojun Chang, Xiaodan Liang
Firstly, the regions of primary interest to radiologists are usually located in a small area of the global image, meaning that the remainder parts of the image could be considered as irrelevant noise in the training procedure.
no code implementations • 19 Jun 2019 • Mingjie Li, Youqian Feng, Zhonghai Yin, Cheng Zhou, Fanghao Dong, Yu-an Lin, Yuhao Dong
Meanwhile, the action recognition network is tested in our gesture and body posture data sets for specific target.
no code implementations • 18 Jun 2019 • Mingjie Li, Youqian Feng, Zhonghai Yin, Cheng Zhou, Fanghao Dong
Common target detection is usually based on single frame images, which is vulnerable to affected by the similar targets in the image and not applicable to video images.
3 code implementations • 1 Jun 2018 • Ke Sun, Mingjie Li, Dong Liu, Jingdong Wang
In this paper, we are interested in building lightweight and efficient convolutional neural networks.