Search Results for author: Mingjie Li

Found 32 papers, 14 papers with code

Implicit Euler Skip Connections: Enhancing Adversarial Robustness via Numerical Stability

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.

Adversarial Attack Adversarial Robustness

Black-box Adversarial Attacks Against Image Quality Assessment Models

no code implementations27 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-Reference Image Quality Assessment NR-IQA

EMBRE: Entity-aware Masking for Biomedical Relation Extraction

no code implementations15 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.

named-entity-recognition Named Entity Recognition +3

Mask Propagation for Efficient Video Semantic Segmentation

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.

Semantic Segmentation Video Semantic Segmentation

Explaining How a Neural Network Play the Go Game and Let People Learn

no code implementations15 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.

Game of Go

Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs

1 code implementation26 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.

Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?

no code implementations3 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.


Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation

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.

Contrastive Learning General Knowledge +2

Does a Neural Network Really Encode Symbolic Concepts?

1 code implementation25 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.

Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation

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.

Clinical Knowledge Medical Report Generation

SymNMF-Net for The Symmetric NMF Problem

no code implementations26 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.


Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs

1 code implementation4 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.

Adversarial Robustness Disentanglement

Visualizing the Emergence of Intermediate Visual Patterns in DNNs

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.

Knowledge Distillation

Generating Watermarked Adversarial Texts

no code implementations25 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.

Adversarial Text Text Generation

Optimization inspired Multi-Branch Equilibrium 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.

Towards Understanding and Improving Dropout in Game Theory

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.

Understanding, Analyzing, and Optimizing the Complexity of Deep Models

no code implementations1 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.


Interpreting and Boosting Dropout from a Game-Theoretic View

no code implementations24 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.

Interpreting and Disentangling Feature Components of Various Complexity from DNNs

1 code implementation29 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.

Knowledge Distillation

Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation

2 code implementations6 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.

Image Captioning Medical Report Generation +1

An Action Recognition network for specific target based on rMC and RPN

no code implementations19 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.

Action Recognition regression

Impoved RPN for Single Targets Detection based on the Anchor Mask Net

no code implementations18 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.

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