Search Results for author: Eric I-Chao Chang

Found 21 papers, 9 papers with code

Exploring Diffusion Time-steps for Unsupervised Representation Learning

1 code implementation21 Jan 2024 Zhongqi Yue, Jiankun Wang, Qianru Sun, Lei Ji, Eric I-Chao Chang, Hanwang Zhang

Representation learning is all about discovering the hidden modular attributes that generate the data faithfully.

Attribute counterfactual +3

Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning

1 code implementation CVPR 2024 Sicong Shen, Yang Zhou, Bingzheng Wei, Eric I-Chao Chang, Yan Xu

However our empirical investigation in this paper reveals that models fine-tuned using existing methods still manifest a high level of model complexity inherited from the pre-training stage leading to a suboptimal stability and generalization ability.

EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images

3 code implementations NeurIPS 2023 Seongsu Bae, Daeun Kyung, Jaehee Ryu, Eunbyeol Cho, Gyubok Lee, Sunjun Kweon, JungWoo Oh, Lei Ji, Eric I-Chao Chang, Tackeun Kim, Edward Choi

To develop our dataset, we first construct two uni-modal resources: 1) The MIMIC-CXR-VQA dataset, our newly created medical visual question answering (VQA) benchmark, specifically designed to augment the imaging modality in EHR QA, and 2) EHRSQL (MIMIC-IV), a refashioned version of a previously established table-based EHR QA dataset.

Decision Making Medical Visual Question Answering +2

3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis

no code implementations18 May 2022 Yang Zhou, Zhiwen Yang, HUI ZHANG, Eric I-Chao Chang, Yubo Fan, Yan Xu

(2) We adopt a task-driven strategy that couples a segmentation task with a generative adversarial network (GAN) framework to improve the translation performance.

Generative Adversarial Network Translation

Whole Brain Segmentation with Full Volume Neural Network

1 code implementation29 Oct 2021 Yeshu Li, Jonathan Cui, Yilun Sheng, Xiao Liang, Jingdong Wang, Eric I-Chao Chang, Yan Xu

To address these issues, we propose to adopt a full volume framework, which feeds the full volume brain image into the segmentation network and directly outputs the segmentation result for the whole brain volume.

Brain Segmentation Representation Learning +1

Microscopic fine-grained instance classification through deep attention

no code implementations6 Oct 2020 Mengran Fan, Tapabrata Chakrabort, Eric I-Chao Chang, Yan Xu, Jens Rittscher

Fine-grained classification of microscopic image data with limited samples is an open problem in computer vision and biomedical imaging.

Classification Deep Attention +2

MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

3 code implementations CVPR 2020 Shengyu Zhao, Yilun Sheng, Yue Dong, Eric I-Chao Chang, Yan Xu

In this paper, we propose an asymmetric occlusion-aware feature matching module, which can learn a rough occlusion mask that filters useless (occluded) areas immediately after feature warping without any explicit supervision.

Optical Flow Estimation

Recursive Cascaded Networks for Unsupervised Medical Image Registration

5 code implementations ICCV 2019 Shengyu Zhao, Yue Dong, Eric I-Chao Chang, Yan Xu

We present recursive cascaded networks, a general architecture that enables learning deep cascades, for deformable image registration.

Image Registration Medical Image Registration

MRI Cross-Modality NeuroImage-to-NeuroImage Translation

no code implementations22 Jan 2018 Qianye Yang, Nannan Li, Zixu Zhao, Xingyu Fan, Eric I-Chao Chang, Yan Xu

Based on our proposed framework, we first propose a method for cross-modality registration by fusing the deformation fields to adopt the cross-modality information from translated modalities.

MRI segmentation Segmentation +1

Unsupervised End-to-end Learning for Deformable Medical Image Registration

no code implementations23 Nov 2017 Siyuan Shan, Wen Yan, Xiaoqing Guo, Eric I-Chao Chang, Yubo Fan, Yan Xu

The contributions of our algorithm are threefold: (1) We transplant traditional image registration algorithms to an end-to-end convolutional neural network framework, while maintaining the unsupervised nature of image registration problems.

Deformable Medical Image Registration Image Registration +1

Constrained Deep Weak Supervision for Histopathology Image Segmentation

no code implementations3 Jan 2017 Zhipeng Jia, Xingyi Huang, Eric I-Chao Chang, Yan Xu

(2) We develop a deep week supervision formulation to exploit multi-scale learning under weak supervision within fully convolutional networks.

Image Segmentation Multiple Instance Learning +2

Learning Multi-level Features For Sensor-based Human Action Recognition

no code implementations22 Nov 2016 Yan Xu, Zhengyang Shen, Xin Zhang, Yifan Gao, Shujian Deng, Yipei Wang, Yubo Fan, Eric I-Chao Chang

This paper proposes a multi-level feature learning framework for human action recognition using a single body-worn inertial sensor.

Action Recognition Temporal Action Localization

Gland Instance Segmentation Using Deep Multichannel Neural Networks

no code implementations21 Nov 2016 Yan Xu, Yang Li, Yipei Wang, Mingyuan Liu, Yubo Fan, Maode Lai, Eric I-Chao Chang

Methods: We leverage the idea of image-to-image prediction in recent deep learning by designing an algorithm that automatically exploits and fuses complex multichannel information - regional, location, and boundary cues - in gland histology images.

Instance Segmentation Segmentation +1

Gland Instance Segmentation by Deep Multichannel Neural Networks

no code implementations17 Jul 2016 Yan Xu, Yang Li, Mingyuan Liu, Yipei Wang, Yubo Fan, Maode Lai, Eric I-Chao Chang

Here we leverage the idea of image-to-image prediction in recent deep learning by building a framework that automatically exploits and fuses complex multichannel information, regional, location and boundary patterns in gland histology images.

Instance Segmentation Segmentation +1

Gland Instance Segmentation by Deep Multichannel Side Supervision

no code implementations12 Jul 2016 Yan Xu, Yang Li, Mingyuan Liu, Yipei Wang, Maode Lai, Eric I-Chao Chang

In this paper, we propose a new image instance segmentation method that segments individual glands (instances) in colon histology images.

Instance Segmentation Segmentation +1

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