Search Results for author: Shen Zheng

Found 14 papers, 9 papers with code

Addressing Source Scale Bias via Image Warping for Domain Adaptation

no code implementations19 Mar 2024 Shen Zheng, Anurag Ghosh, Srinivasa G. Narasimhan

Discovering that shifting the source scale distribution improves backbone features, we developed a instance-level warping guidance aimed at object region sampling to mitigate source scale bias in domain adaptation.

Domain Adaptation Object

TPSeNCE: Towards Artifact-Free Realistic Rain Generation for Deraining and Object Detection in Rain

1 code implementation1 Nov 2023 Shen Zheng, Changjie Lu, Srinivasa G. Narasimhan

We first introduce a Triangular Probability Similarity (TPS) constraint to guide the generated images toward clear and rainy images in the discriminator manifold, thereby minimizing artifacts and distortions during rain generation.

Contrastive Learning Image-to-Image Translation +6

GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond

1 code implementation28 Sep 2023 Shen Zheng, Yuyu Zhang, Yijie Zhu, Chenguang Xi, Pengyang Gao, Xun Zhou, Kevin Chen-Chuan Chang

With the rapid advancement of large language models (LLMs), there is a pressing need for a comprehensive evaluation suite to assess their capabilities and limitations.

Benchmarking

Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage

1 code implementation22 May 2023 Hanyin Shao, Jie Huang, Shen Zheng, Kevin Chen-Chuan Chang

The advancement of large language models (LLMs) brings notable improvements across various applications, while simultaneously raising concerns about potential private data exposure.

Why Does ChatGPT Fall Short in Providing Truthful Answers?

no code implementations20 Apr 2023 Shen Zheng, Jie Huang, Kevin Chen-Chuan Chang

To better understand the model's particular weaknesses in providing truthful answers, we embark an in-depth exploration of open-domain question answering.

Memorization Open-Domain Question Answering +1

Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyond

1 code implementation21 Dec 2022 Shen Zheng, Yiling Ma, Jinqian Pan, Changjie Lu, Gaurav Gupta

This paper presents a comprehensive survey of low-light image and video enhancement, addressing two primary challenges in the field.

Low-Light Image Enhancement Video Enhancement

AS-IntroVAE: Adversarial Similarity Distance Makes Robust IntroVAE

1 code implementation28 Jun 2022 Changjie Lu, Shen Zheng, ZiRui Wang, Omar Dib, Gaurav Gupta

However, due to the unavailability of an effective metric to evaluate the difference between the real and the fake images, the posterior collapse and the vanishing gradient problem still exist, reducing the fidelity of the synthesized images.

Image Generation

Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximization

1 code implementation20 Apr 2022 Changjie Lu, Shen Zheng, Gaurav Gupta

This paper introduces UDA-VAE++, an unsupervised domain adaptation framework for cardiac segmentation with a compact loss function lower bound.

Cardiac Segmentation Image Segmentation +4

Asian Giant Hornet Control based on Image Processing and Biological Dispersal

no code implementations26 Nov 2021 Changjie Lu, Shen Zheng, Hailu Qiu

Fourth, we apply ordinary differential equations to examine AGH numbers at the different natural growthrate and reaction speed and output the potential propagation coefficient.

Feature Importance

SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Deraining

1 code implementation17 Nov 2021 Shen Zheng, Changjie Lu, Yuxiong Wu, Gaurav Gupta

To address this issue, in this paper, we present a segmentation-aware progressive network (SAPNet) based upon contrastive learning for single image deraining.

Contrastive Learning Image Restoration +5

Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement

1 code implementation3 Oct 2021 Shen Zheng, Gaurav Gupta

Firstly, we design an enhancement factor extraction network using depthwise separable convolution for an efficient estimate of the pixel-wise light deficiency of an low-light image.

Low-Light Image Enhancement Segmentation +3

Exploiting Spline Models for the Training of Fully Connected Layers in Neural Network

no code implementations12 Feb 2021 Kanya Mo, Shen Zheng, Xiwei Wang, Jinghua Wang, Klaus-Dieter Schewe

The fully connected (FC) layer, one of the most fundamental modules in artificial neural networks (ANN), is often considered difficult and inefficient to train due to issues including the risk of overfitting caused by its large amount of parameters.

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