Search Results for author: Ye Luo

Found 18 papers, 2 papers with code

Equalized Focal Loss for Dense Long-Tailed Object Detection

1 code implementation CVPR 2022 Bo Li, Yongqiang Yao, Jingru Tan, Gang Zhang, Fengwei Yu, Jianwei Lu, Ye Luo

The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem.

object-detection Object Detection

Self-fulfilling Bandits: Dynamic Selection in Algorithmic Decision-making

no code implementations28 Aug 2021 Jin Li, Ye Luo, Xiaowei Zhang

This paper identifies and addresses dynamic selection problems that arise in online learning algorithms with endogenous data.

Decision Making online learning

PoissonSeg: Semi-Supervised Few-Shot Medical Image Segmentation via Poisson Learning

no code implementations26 Aug 2021 Xiaoang Shen, Guokai Zhang, Huilin Lai, Jihao Luo, Jianwei Lu, Ye Luo

The application of deep learning to medical image segmentation has been hampered due to the lack of abundant pixel-level annotated data.

Few-Shot Semantic Segmentation Image Segmentation +4

Causal Reinforcement Learning: An Instrumental Variable Approach

no code implementations6 Mar 2021 Jin Li, Ye Luo, Xiaowei Zhang

In the standard data analysis framework, data is first collected (once for all), and then data analysis is carried out.

Causal Inference reinforcement-learning

Deblurring Processor for Motion-Blurred Faces Based on Generative Adversarial Networks

no code implementations3 Mar 2021 Shiqing Fan, Ye Luo

Then we conducted a motion blur image generation experiment on some general facial data set, and used the pairs of blurred and sharp face image data to perform the training and testing experiments of the processor GAN, and gave some visual displays.

Deblurring Face Detection +3

Min-Max-Plus Neural Networks

no code implementations12 Feb 2021 Ye Luo, Shiqing Fan

We present a new model of neural networks called Min-Max-Plus Neural Networks (MMP-NNs) based on operations in tropical arithmetic.

L-SNet: from Region Localization to Scale Invariant Medical Image Segmentation

no code implementations11 Feb 2021 Jiahao Xie, Sheng Zhang, Jianwei Lu, Ye Luo

Coarse-to-fine models and cascade segmentation architectures are widely adopted to solve the problem of large scale variations in medical image segmentation.

Image Segmentation Medical Image Segmentation +1

Cross-Modal Self-Attention Distillation for Prostate Cancer Segmentation

no code implementations8 Nov 2020 Guokai Zhang, Xiaoang Shen, Ye Luo, Jihao Luo, Zeju Wang, Weigang Wang, Binghui Zhao, Jianwei Lu

In this paper, we develop a cross-modal self-attention distillation network by fully exploiting the encoded information of the intermediate layers from different modalities, and the extracted attention maps of different modalities enable the model to transfer the significant spatial information with more details.

Image Segmentation Medical Image Segmentation +1

Adaptive Discrete Smoothing for High-Dimensional and Nonlinear Panel Data

no code implementations30 Dec 2019 Xi Chen, Ye Luo, Martin Spindler

In this paper we develop a data-driven smoothing technique for high-dimensional and non-linear panel data models.

BIG-bench Machine Learning

Shape-Enforcing Operators for Point and Interval Estimators

no code implementations4 Sep 2018 Xi Chen, Victor Chernozhukov, Iván Fernández-Val, Scott Kostyshak, Ye Luo

A common problem in econometrics, statistics, and machine learning is to estimate and make inference on functions that satisfy shape restrictions.


Estimation and Inference of Treatment Effects with $L_2$-Boosting in High-Dimensional Settings

no code implementations31 Dec 2017 Jannis Kueck, Ye Luo, Martin Spindler, Zigan Wang

In this paper, we provide results for valid inference after post- or orthogonal $L_2$-Boosting is used for variable selection.

Variable Selection

$L_2$Boosting for Economic Applications

no code implementations10 Feb 2017 Ye Luo, Martin Spindler

In the recent years more and more high-dimensional data sets, where the number of parameters $p$ is high compared to the number of observations $n$ or even larger, are available for applied researchers.

High-Dimensional $L_2$Boosting: Rate of Convergence

no code implementations29 Feb 2016 Ye Luo, Martin Spindler, Jannis Kück

Finally, we present simulation studies and applications to illustrate the relevance of our theoretical results and to provide insights into the practical aspects of boosting.

The Sorted Effects Method: Discovering Heterogeneous Effects Beyond Their Averages

1 code implementation17 Dec 2015 Victor Chernozhukov, Ivan Fernandez-Val, Ye Luo

They are as convenient and easy to report in practice as the conventional average partial effects.

Methodology Econometrics

Actionness-Assisted Recognition of Actions

no code implementations ICCV 2015 Ye Luo, Loong-Fah Cheong, An Tran

We elicit from a fundamental definition of action low-level attributes that can reveal agency and intentionality.

Action Detection Action Recognition

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