198 citations · 282 across the 14 of their papers we have counts for
14 papers
Multi-Modal Representation Learning via Semi-Supervised Rate Reduction for Generalized Category Discovery
Wei He, Xianghan Meng, Zhiyuan Huang +3
Generalized Category Discovery (GCD) aims to identify both known and unknown categories, with only partial labels given for the known categories, posing a challenging open-set reco…
Delving into Muon and Beyond: Deep Analysis and Extensions
Xianbiao Qi, Marco Chen, Jiaquan Ye +2
The Muon optimizer has recently attracted considerable attention for its strong empirical performance and use of orthogonalized updates on matrix-shaped parameters, yet its underly…
SimpleGPT: Improving GPT via A Simple Normalization Strategy
Marco Chen, Xianbiao Qi, Yelin He +2
In this work, we revisit Transformer optimization through the lens of second-order geometry and establish a direct connection between architectural design, activation scale, the He…
Taming Transformer Without Using Learning Rate Warmup
Xianbiao Qi, Yelin He, Jiaquan Ye +5
Scaling Transformer to a large scale without using some technical tricks such as learning rate warump and using an obviously lower learning rate is an extremely challenging task, a…
Exploring a Principled Framework for Deep Subspace Clustering
Xianghan Meng, Zhiyuan Huang, Wei He +3
Subspace clustering is a classical unsupervised learning task, built on a basic assumption that high-dimensional data can be approximated by a union of subspaces (UoS). Nevertheles…
Neural Normalized Cut: A Differential and Generalizable Approach for Spectral Clustering
Wei He, Shangzhi Zhang, Chun-Guang Li +3
Spectral clustering, as a popular tool for data clustering, requires an eigen-decomposition step on a given affinity to obtain the spectral embedding. Nevertheless, such a step suf…
1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection
Yuxiang Zhong, Xianbiao Qi, Shanjun Li +4
In this technical report, we present our 1st place solution for the ICDAR 2021 competition on mathematical formula detection (MFD). The MFD task has three key challenges including…
PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML
Jiaquan Ye, Xianbiao Qi, Yelin He +4
This paper presents our solution for ICDAR 2021 competition on scientific literature parsing taskB: table recognition to HTML. In our method, we divide the table content recognitio…
PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex
Yelin He, Xianbiao Qi, Jiaquan Ye +5
This paper presents our solution for the ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX. This competition has two sub-tasks: Table Structure Reconstruction (…
Learning Graph Normalization for Graph Neural Networks
Yihao Chen, Xin Tang, Xianbiao Qi +2
Graph Neural Networks (GNNs) have attracted considerable attention and have emerged as a new promising paradigm to process graph-structured data. GNNs are usually stacked to multip…
Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition
Bingcong Li, Xin Tang, Xianbiao Qi +2
Recently, inspired by Transformer, self-attention-based scene text recognition approaches have achieved outstanding performance. However, we find that the size of model expands rap…
PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
Wenwen Yu, Ning Lu, Xianbiao Qi +2
Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition ta…
Neural Mesh Refiner for 6-DoF Pose Estimation
Di Wu, Yihao Chen, Xianbiao Qi +3
How can we effectively utilise the 2D monocular image information for recovering the 6D pose (6-DoF) of the visual objects? Deep learning has shown to be effective for robust and r…
MASTER: Multi-Aspect Non-local Network for Scene Text Recognition
Ning Lu, Wenwen Yu, Xianbiao Qi +4
Attention-based scene text recognizers have gained huge success, which leverages a more compact intermediate representation to learn 1d- or 2d- attention by a RNN-based encoder-dec…