18 citations · 38 across the 9 of their papers we have counts for
9 papers
TextBoost: Boosting Scene Text Fidelity in Ultra-low Bitrate Image Compression
Bingxin Wang, Yuan Lan, Zhaoyi Sun +2
Ultra-low bitrate image compression faces a critical challenge: preserving small-font scene text while maintaining overall visual quality. Region-of-interest (ROI) bit allocation c…
ElasticLaneNet: An Efficient Geometry-Flexible Approach for Lane Detection
Yaxin Feng, Yuan Lan, Luchan Zhang +1
The task of lane detection involves identifying the boundaries of driving areas in real-time. Recognizing lanes with variable and complex geometric structures remains a challenge.…
Elastic Interaction Energy-Informed Real-Time Traffic Scene Perception
Yaxin Feng, Yuan Lan, Luchan Zhang +2
Urban segmentation and lane detection are two important tasks for traffic scene perception. Accuracy and fast inference speed of visual perception are crucial for autonomous drivin…
Energy stable neural network for gradient flow equations
Yue Wu, Tianyu Jin, Chuqi Chen +4
We propose an energy stable network (EStable-Net) for solving gradient flow equations. The EStable-Net enables decreasing of a discrete energy along the neural network, which is co…
Large Transformers are Better EEG Learners
Bingxin Wang, Xiaowen Fu, Yuan Lan +3
Pre-trained large transformer models have achieved remarkable performance in the fields of natural language processing and computer vision. However, the limited availability of pub…
DOSnet as a Non-Black-Box PDE Solver: When Deep Learning Meets Operator Splitting
Yuan Lan, Zhen Li, Jie Sun +1
Deep neural networks (DNNs) recently emerged as a promising tool for analyzing and solving complex differential equations arising in science and engineering applications. Alternati…
GOLLIC: Learning Global Context beyond Patches for Lossless High-Resolution Image Compression
Yuan Lan, Liang Qin, Zhaoyi Sun +2
Neural-network-based approaches recently emerged in the field of data compression and have already led to significant progress in image compression, especially in achieving a highe…
Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks
Yue Wu, Yuan Lan, Luchan Zhang +1
Pruning is a model compression method that removes redundant parameters in deep neural networks (DNNs) while maintaining accuracy. Most available filter pruning methods require com…
An Elastic Interaction-Based Loss Function for Medical Image Segmentation
Yuan Lan, Yang Xiang, Luchan Zhang
Deep learning techniques have shown their success in medical image segmentation since they are easy to manipulate and robust to various types of datasets. The commonly used loss fu…