Search Results for author: Xianbiao Qi

Found 28 papers, 9 papers with code

Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices

no code implementations5 Sep 2023 Bojia Zi, Xianbiao Qi, Lingzhi Wang, Jianan Wang, Kam-Fai Wong, Lei Zhang

In this paper, we present Delta-LoRA, which is a novel parameter-efficient approach to fine-tune large language models (LLMs).

DreamTime: An Improved Optimization Strategy for Text-to-3D Content Creation

no code implementations21 Jun 2023 Yukun Huang, Jianan Wang, Yukai Shi, Xianbiao Qi, Zheng-Jun Zha, Lei Zhang

Text-to-image diffusion models pre-trained on billions of image-text pairs have recently enabled text-to-3D content creation by optimizing a randomly initialized Neural Radiance Fields (NeRF) with score distillation.

Image Generation Text to 3D

Understanding Optimization of Deep Learning via Jacobian Matrix and Lipschitz Constant

no code implementations15 Jun 2023 Xianbiao Qi, Jianan Wang, Lei Zhang

This article provides a comprehensive understanding of optimization in deep learning, with a primary focus on the challenges of gradient vanishing and gradient exploding, which normally lead to diminished model representational ability and training instability, respectively.

detrex: Benchmarking Detection Transformers

1 code implementation12 Jun 2023 Tianhe Ren, Shilong Liu, Feng Li, Hao Zhang, Ailing Zeng, Jie Yang, Xingyu Liao, Ding Jia, Hongyang Li, He Cao, Jianan Wang, Zhaoyang Zeng, Xianbiao Qi, Yuhui Yuan, Jianwei Yang, Lei Zhang

To address this issue, we develop a unified, highly modular, and lightweight codebase called detrex, which supports a majority of the mainstream DETR-based instance recognition algorithms, covering various fundamental tasks, including object detection, segmentation, and pose estimation.

Benchmarking object-detection +2

LipsFormer: Introducing Lipschitz Continuity to Vision Transformers

1 code implementation19 Apr 2023 Xianbiao Qi, Jianan Wang, Yihao Chen, Yukai Shi, Lei Zhang

In contrast to previous practical tricks that address training instability by learning rate warmup, layer normalization, attention formulation, and weight initialization, we show that Lipschitz continuity is a more essential property to ensure training stability.

DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training

1 code implementation CVPR 2023 Yihao Chen, Xianbiao Qi, Jianan Wang, Lei Zhang

In this way, we can reduce the GPU memory consumption of contrastive loss computation from $\bigO(B^2)$ to $\bigO(\frac{B^2}{N})$, where $B$ and $N$ are the batch size and the number of GPUs used for training.

Contrastive Learning

Exploring Vision Transformers as Diffusion Learners

no code implementations28 Dec 2022 He Cao, Jianan Wang, Tianhe Ren, Xianbiao Qi, Yihao Chen, Yuan YAO, Lei Zhang

We further provide a hypothesis on the implication of disentangling the generative backbone as an encoder-decoder structure and show proof-of-concept experiments verifying the effectiveness of a stronger encoder for generative tasks with ASymmetriC ENcoder Decoder (ASCEND).

DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

7 code implementations ICLR 2022 Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, Lei Zhang

We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR.

Object Detection

1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection

1 code implementation12 Jul 2021 Yuxiang Zhong, Xianbiao Qi, Shanjun Li, Dengyi Gu, Yihao Chen, Peiyang Ning, Rong Xiao

In this technical report, we present our 1st place solution for the ICDAR 2021 competition on mathematical formula detection (MFD).

PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML

2 code implementations5 May 2021 Jiaquan Ye, Xianbiao Qi, Yelin He, Yihao Chen, Dengyi Gu, Peng Gao, Rong Xiao

In our method, we divide the table content recognition task into foursub-tasks: table structure recognition, text line detection, text line recognition, and box assignment. Our table structure recognition algorithm is customized based on MASTER [1], a robust image textrecognition algorithm.

Line Detection Table Recognition

Learning Graph Normalization for Graph Neural Networks

1 code implementation24 Sep 2020 Yihao Chen, Xin Tang, Xianbiao Qi, Chun-Guang Li, Rong Xiao

We conduct extensive experiments on benchmark datasets for different tasks, including node classification, link prediction, graph classification and graph regression, and confirm that the learned graph normalization leads to competitive results and that the learned weights suggest the appropriate normalization techniques for the specific task.

Graph Classification Graph Regression +2

PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks

2 code implementations16 Apr 2020 Wenwen Yu, Ning Lu, Xianbiao Qi, Ping Gong, Rong Xiao

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 tasks recently.

Graph Learning Key Information Extraction +3

Neural Mesh Refiner for 6-DoF Pose Estimation

no code implementations17 Mar 2020 Di Wu, Yihao Chen, Xianbiao Qi, Yongjian Yu, Weixuan Chen, Rong Xiao

We utilise the overlay between the accurate mask prediction and less accurate mesh prediction to iteratively optimise the direct regressed 6D pose information with a focus on translation estimation.

Autonomous Driving Instance Segmentation +4

MASTER: Multi-Aspect Non-local Network for Scene Text Recognition

7 code implementations7 Oct 2019 Ning Lu, Wenwen Yu, Xianbiao Qi, Yihao Chen, Ping Gong, Rong Xiao, Xiang Bai

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-decoder architecture.

Scene Text Recognition

Self-Supervised Convolutional Subspace Clustering Network

no code implementations CVPR 2019 Junjian Zhang, Chun-Guang Li, Chong You, Xianbiao Qi, Honggang Zhang, Jun Guo, Zhouchen Lin

However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces.

Clustering Image Clustering

Homocentric Hypersphere Feature Embedding for Person Re-identification

no code implementations24 Apr 2018 Wangmeng Xiang, Jianqiang Huang, Xianbiao Qi, Xian-Sheng Hua, Lei Zhang

Person re-identification (Person ReID) is a challenging task due to the large variations in camera viewpoint, lighting, resolution, and human pose.

Person Re-Identification

Face Recognition via Centralized Coordinate Learning

no code implementations17 Jan 2018 Xianbiao Qi, Lei Zhang

Owe to the rapid development of deep neural network (DNN) techniques and the emergence of large scale face databases, face recognition has achieved a great success in recent years.

Classification Face Recognition +2

3D Surface Detail Enhancement From a Single Normal Map

no code implementations ICCV 2017 Wuyuan Xie, Miaohui Wang, Xianbiao Qi, Lei Zhang

In 3D reconstruction, the obtained surface details are mainly limited to the visual sensor due to sampling and quantization in the digitalization process.

3D Reconstruction Quantization

LOAD: Local Orientation Adaptive Descriptor for Texture and Material Classification

no code implementations22 Apr 2015 Xianbiao Qi, Guoying Zhao, Linlin Shen, Qingquan Li, Matti Pietikainen

It is worth to mention that we achieve a 65. 4\% classification accuracy-- which is, to the best of our knowledge, the highest record by far --on Flickr Material Database by using a single feature.

General Classification Material Classification +2

HEp-2 Cell Classification via Fusing Texture and Shape Information

no code implementations16 Feb 2015 Xianbiao Qi, Guoying Zhao, Chun-Guang Li, Jun Guo, Matti Pietikäinen

Indirect Immunofluorescence (IIF) HEp-2 cell image is an effective evidence for diagnosis of autoimmune diseases.

Classification General Classification

Dynamic texture and scene classification by transferring deep image features

no code implementations1 Feb 2015 Xianbiao Qi, Chun-Guang Li, Guoying Zhao, Xiaopeng Hong, Matti Pietikäinen

Moreover we explore two different implementations of the TCoF scheme, i. e., the \textit{spatial} TCoF and the \textit{temporal} TCoF, in which the mean-removed frames and the difference between two adjacent frames are used as the inputs of the ConvNet, respectively.

Classification General Classification +2

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