Search Results for author: Mingchen Gao

Found 28 papers, 10 papers with code

FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation

1 code implementation16 Oct 2021 Yan Shen, Jian Du, Han Zhao, Benyu Zhang, Zhanghexuan Ji, Mingchen Gao

Federated adversary domain adaptation is a unique distributed minimax training task due to the prevalence of label imbalance among clients, with each client only seeing a subset of the classes of labels required to train a global model.

Domain Adaptation

Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness

1 code implementation ICCV 2021 Zhenyi Wang, Tiehang Duan, Le Fang, Qiuling Suo, Mingchen Gao

In this paper, we explore a more practical and challenging setting where task distribution changes over time with domain shift.

Change Detection Management +1

Improving Task-free Continual Learning by Distributionally Robust Memory Evolution

1 code implementation15 Jul 2022 Zhenyi Wang, Li Shen, Le Fang, Qiuling Suo, Tiehang Duan, Mingchen Gao

To address these problems, for the first time, we propose a principled memory evolution framework to dynamically evolve the memory data distribution by making the memory buffer gradually harder to be memorized with distributionally robust optimization (DRO).

Continual Learning

Learning To Learn and Remember Super Long Multi-Domain Task Sequence

1 code implementation CVPR 2022 Zhenyi Wang, Li Shen, Tiehang Duan, Donglin Zhan, Le Fang, Mingchen Gao

We propose a domain shift detection technique to capture latent domain change and equip the meta optimizer with it to work in this setting.

Meta-Learning

Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data

1 code implementation20 Sep 2019 Chunwei Ma, Zhanghexuan Ji, Mingchen Gao

Three-dimensional medical image segmentation is one of the most important problems in medical image analysis and plays a key role in downstream diagnosis and treatment.

Benchmarking Ensemble Learning +6

Improving Joint Learning of Chest X-Ray and Radiology Report by Word Region Alignment

1 code implementation4 Sep 2021 Zhanghexuan Ji, Mohammad Abuzar Shaikh, Dana Moukheiber, Sargur Srihari, Yifan Peng, Mingchen Gao

Self-supervised learning provides an opportunity to explore unlabeled chest X-rays and their associated free-text reports accumulated in clinical routine without manual supervision.

Representation Learning Self-Supervised Learning +1

Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach

1 code implementation5 Feb 2022 Chunwei Ma, Ziyun Huang, Mingchen Gao, Jinhui Xu

One observation is that the widely embraced ProtoNet model is essentially a Voronoi Diagram (VD) in the feature space.

Few-Shot Learning

Improving Uncertainty Calibration of Deep Neural Networks via Truth Discovery and Geometric Optimization

1 code implementation25 Jun 2021 Chunwei Ma, Ziyun Huang, Jiayi Xian, Mingchen Gao, Jinhui Xu

Deep Neural Networks (DNNs), despite their tremendous success in recent years, could still cast doubts on their predictions due to the intrinsic uncertainty associated with their learning process.

Holistic Interstitial Lung Disease Detection using Deep Convolutional Neural Networks: Multi-label Learning and Unordered Pooling

no code implementations19 Jan 2017 Mingchen Gao, Ziyue Xu, Le Lu, Adam P. Harrison, Ronald M. Summers, Daniel J. Mollura

Accurately predicting and detecting interstitial lung disease (ILD) patterns given any computed tomography (CT) slice without any pre-processing prerequisites, such as manually delineated regions of interest (ROIs), is a clinically desirable, yet challenging goal.

Computed Tomography (CT) Multi-Label Learning +1

Brain Tumor Segmentation on MRI with Missing Modalities

no code implementations15 Apr 2019 Yan Shen, Mingchen Gao

We design a brain tumor segmentation algorithm that is robust to the absence of any modality.

Brain Tumor Segmentation Domain Adaptation +2

Scribble-based Hierarchical Weakly Supervised Learning for Brain Tumor Segmentation

no code implementations5 Nov 2019 Zhanghexuan Ji, Yan Shen, Chunwei Ma, Mingchen Gao

In this paper, we use only two kinds of weak labels, i. e., scribbles on whole tumor and healthy brain tissue, and global labels for the presence of each substructure, to train a deep learning model to segment all the sub-regions.

Brain Tumor Segmentation Clustering +4

A Stochastic Gradient Langevin Dynamics Algorithm For Noise Intrinsic Federated Learning

no code implementations1 Jan 2021 Yan Shen, Jian Du, Chunwei Ma, Mingchen Gao, Benyu Zhang

Our introduced SGLD oracle would lower generalization errors in local node's parameter learning and provide local node DP protections.

Federated Learning

An End-to-End learnable Flow Regularized Model for Brain Tumor Segmentation

no code implementations1 Sep 2021 Yan Shen, Zhanghexuan Ji, Mingchen Gao

Many segmentation tasks for biomedical images can be modeled as the minimization of an energy function and solved by a class of max-flow and min-cut optimization algorithms.

Brain Tumor Segmentation Segmentation +1

LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation

no code implementations4 Sep 2021 Mohammad Abuzar Shaikh, Zhanghexuan Ji, Dana Moukheiber, Yan Shen, Sargur Srihari, Mingchen Gao

Pre-training visual and textual representations from large-scale image-text pairs is becoming a standard approach for many downstream vision-language tasks.

Image Captioning Image Generation +2

Few-shot Learning via Dirichlet Tessellation Ensemble

no code implementations ICLR 2022 Chunwei Ma, Ziyun Huang, Mingchen Gao, Jinhui Xu

One observation is that the widely embraced ProtoNet model is essentially a Dirichlet Tessellation (Voronoi Diagram) in the feature space.

Few-Shot Learning

A Bayesian Detect to Track System for Robust Visual Object Tracking and Semi-Supervised Model Learning

no code implementations5 May 2022 Yan Shen, Zhanghexuan Ji, Chunwei Ma, Mingchen Gao

Based on our particle filter inference algorithm, a semi-supervised learn-ing algorithm is utilized for learning tracking network on intermittent labeled frames by variational inference.

Variational Inference Visual Object Tracking

Learning Individual Interactions from Population Dynamics with Discrete-Event Simulation Model

no code implementations4 May 2022 Yan Shen, Fan Yang, Mingchen Gao, Wen Dong

Traditional machine learning approaches capture complex system dynamics either with dynamic Bayesian networks and state space models, which is hard to scale because it is non-trivial to prescribe the dynamics with a sparse graph or a system of differential equations; or a deep neural networks, where the distributed representation of the learned dynamics is hard to interpret.

Progressive Voronoi Diagram Subdivision: Towards A Holistic Geometric Framework for Exemplar-free Class-Incremental Learning

no code implementations28 Jul 2022 Chunwei Ma, Zhanghexuan Ji, Ziyun Huang, Yan Shen, Mingchen Gao, Jinhui Xu

Exemplar-free Class-incremental Learning (CIL) is a challenging problem because rehearsing data from previous phases is strictly prohibited, causing catastrophic forgetting of Deep Neural Networks (DNNs).

Class Incremental Learning Incremental Learning +1

Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions

1 code implementation3 Sep 2022 Zhenyi Wang, Li Shen, Le Fang, Qiuling Suo, Donglin Zhan, Tiehang Duan, Mingchen Gao

Two key challenges arise in this more realistic setting: (i) how to use unlabeled data in the presence of a large amount of unlabeled out-of-distribution (OOD) data; and (ii) how to prevent catastrophic forgetting on previously learned task distributions due to the task distribution shift.

Meta-Learning

MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation

no code implementations CVPR 2023 Zhenyi Wang, Li Shen, Donglin Zhan, Qiuling Suo, Yanjun Zhu, Tiehang Duan, Mingchen Gao

To make them trustworthy and robust to corruptions deployed in safety-critical scenarios, we propose a meta-learning framework of self-adaptive data augmentation to tackle the corruption robustness in CL.

Continual Learning Data Augmentation +1

Continual Domain Adversarial Adaptation via Double-Head Discriminators

no code implementations5 Feb 2024 Yan Shen, Zhanghexuan Ji, Chunwei Ma, Mingchen Gao

We prove that with the introduction of a pre-trained source-only domain discriminator, the empirical estimation error of $\gH$-divergence related adversarial loss is reduced from the source domain side.

Continual Learning Domain Adaptation

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