Search Results for author:
Found 16 papers, 11 papers with code
Learn to Recover Visible Color for Video Surveillance in a Day
In silicon sensors, the interference between visible and near-infrared (NIR) signals is a crucial problem.
Driving Style Alignment for LLM-powered Driver Agent
Recently, LLM-powered driver agents have demonstrated considerable potential in the field of autonomous driving, showcasing human-like reasoning and decision-making abilities. However, current research on aligning driver agent behaviors with human driving styles remains limited, partly due to the scarcity of high-quality natural language data from human driving behaviors. To address this research gap, we propose a multi-alignment framework designed to align driver agents with human driving styles through demonstrations and feedback.
CBQ: Cross-Block Quantization for Large Language Models
Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs.
Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks
Although Negative Data Augmentation (NDA) effectively enhances unconditional and class-conditional GANs by introducing anomalies into real training images, guiding the GANs away from low-quality outputs, its impact on CcGANs is limited, as it fails to replicate negative samples that may occur during the CcGAN sampling.
Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images
Four tiny SOAP models are also created by replacing the convolutional blocks in Mobile-SOAP with four small-scale networks, respectively.
A Scale-Arbitrary Image Super-Resolution Network Using Frequency-domain Information
Image super-resolution (SR) is a technique to recover lost high-frequency information in low-resolution (LR) images.
Delving into Deep Image Prior for Adversarial Defense: A Novel Reconstruction-based Defense Framework
Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images.
Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression
Knowledge distillation (KD) has been actively studied for image classification tasks in deep learning, aiming to improve the performance of a student based on the knowledge from a teacher.
Efficient Subsampling of Realistic Images From GANs Conditional on a Class or a Continuous Variable
When sampling from CcGANs, the superiority of cDR-RS is even more noticeable in terms of both effectiveness and efficiency.
Ranked #1 on
Image Generation
on RC-49
Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms
This work proposes the continuous conditional generative adversarial network (CcGAN), the first generative model for image generation conditional on continuous, scalar conditions (termed regression labels).
Ranked #2 on
Image Generation
on RC-49
Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection
Specially, when adversaries consider imperceptibility as a constraint, the proposed anti-forensic method can improve the average attack success rate by around 30\% on fake face images over two baseline attacks.
Classification Beats Regression: Counting of Cells from Greyscale Microscopic Images based on Annotation-free Training Samples
Modern methods often formulate the counting of cells from microscopic images as a regression problem and more or less rely on expensive, manually annotated training images (e. g., dot annotations indicating the centroids of cells or segmentation masks identifying the contours of cells).
A Novel Neural Network Training Framework with Data Assimilation
In data assimilation algorithms, the error covariance between the forecasts and observations is used to optimize the parameters.
Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss
Our subsampling methods do not rely on the optimality of the discriminator and are suitable for all types of GANs.
Sparse transition matrix estimation for high-dimensional and locally stationary vector autoregressive models
Under the sparsity assumption on the transition matrix, we establish the rate of convergence of the proposed estimator and show that the convergence rate depends on the smoothness of the locally stationary VAR processes only through the smoothness of the transition matrix function.
Statistics Theory Applications Statistics Theory
Joint Sensing Matrix and Sparsifying Dictionary Optimization for Tensor Compressive Sensing
In this paper, we propose a joint optimization approach of the sensing matrix and dictionary for a TCS system.
