Search Results for author: Qi Song

Found 31 papers, 6 papers with code

How Self-Attention Improves Rare Class Performance in a Question-Answering Dialogue Agent

no code implementations SIGDIAL (ACL) 2020 Adam Stiff, Qi Song, Eric Fosler-Lussier

Contextualized language modeling using deep Transformer networks has been applied to a variety of natural language processing tasks with remarkable success.

Language Modelling Question Answering +1

LLMBind: A Unified Modality-Task Integration Framework

no code implementations22 Feb 2024 Bin Zhu, Peng Jin, Munan Ning, Bin Lin, Jinfa Huang, Qi Song, Jiaxi Cui, Junwu Zhang, Zhenyu Tang, Mingjun Pan, Xing Zhou, Li Yuan

While recent progress in multimodal large language models tackles various modality tasks, they posses limited integration capabilities for complex multi-modality tasks, consequently constraining the development of the field.

Audio Generation Image Segmentation +1

Generative Steganographic Flow

no code implementations10 May 2023 Ping Wei, Ge Luo, Qi Song, Xinpeng Zhang, Zhenxing Qian, Sheng Li

In the forward mapping, secret data is hidden in the input latent of Glow model to generate stego images.

Image Generation

Synergistic Network Learning and Label Correction for Noise-robust Image Classification

no code implementations27 Feb 2022 Chen Gong, Kong Bin, Eric J. Seibel, Xin Wang, Youbing Yin, Qi Song

Taking the expertise of DNNs to learn meaningful patterns before fitting noise, our framework first trains two networks over the current dataset with small loss selection.

Image Classification

Recursive Least Squares for Training and Pruning Convolutional Neural Networks

no code implementations13 Jan 2022 Tianzong Yu, Chunyuan Zhang, YuAn Wang, Meng Ma, Qi Song

Convolutional neural networks (CNNs) have succeeded in many practical applications.

Recursive Least Squares Policy Control with Echo State Network

no code implementations13 Jan 2022 Chunyuan Zhang, Chao Liu, Qi Song, Jie Zhao

However, limited by the strong correlation among sequential samples of the agent, ESN-based policy control algorithms are difficult to use the recursive least squares (RLS) algorithm to update the ESN's parameters.

Time Series Time Series Analysis

Stochastic Actor-Executor-Critic for Image-to-Image Translation

1 code implementation14 Dec 2021 Ziwei Luo, Jing Hu, Xin Wang, Siwei Lyu, Bin Kong, Youbing Yin, Qi Song, Xi Wu

Training a model-free deep reinforcement learning model to solve image-to-image translation is difficult since it involves high-dimensional continuous state and action spaces.

Continuous Control Image-to-Image Translation +3

Fully Attentional Network for Semantic Segmentation

1 code implementation8 Dec 2021 Qi Song, Jie Li, Chenghong Li, Hao Guo, Rui Huang

Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation.

Computational Efficiency Segmentation +1

Denoised Non-Local Neural Network for Semantic Segmentation

no code implementations27 Oct 2021 Qi Song, Jie Li, Hao Guo, Rui Huang

Without any external training data, our proposed Denoised NL can achieve the state-of-the-art performance of 83. 5\% and 46. 69\% mIoU on Cityscapes and ADE20K, respectively.

Semantic Segmentation

Revisiting Recursive Least Squares for Training Deep Neural Networks

no code implementations7 Sep 2021 Chunyuan Zhang, Qi Song, Hui Zhou, Yigui Ou, Hongyao Deng, Laurence Tianruo Yang

In this paper, to overcome these drawbacks, we propose three novel RLS optimization algorithms for training feedforward neural networks, convolutional neural networks and recurrent neural networks (including long short-term memory networks), by using the error backpropagation and our average-approximation RLS method, together with the equivalent gradients of the linear least squares loss function with respect to the linear outputs of hidden layers.

Imperceptible Adversarial Examples for Fake Image Detection

no code implementations3 Jun 2021 Quanyu Liao, Yuezun Li, Xin Wang, Bin Kong, Bin Zhu, Siwei Lyu, Youbing Yin, Qi Song, Xi Wu

Fooling people with highly realistic fake images generated with Deepfake or GANs brings a great social disturbance to our society.

Face Swapping Fake Image Detection

Transferable Adversarial Examples for Anchor Free Object Detection

no code implementations3 Jun 2021 Quanyu Liao, Xin Wang, Bin Kong, Siwei Lyu, Bin Zhu, Youbing Yin, Qi Song, Xi Wu

Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change prediction result.

Adversarial Attack Object +2

AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing

1 code implementation10 Mar 2021 Qi Song, Kangfu Mei, Rui Huang

In this paper, we propose a new model, called Attention-Augmented Network (AttaNet), to capture both global context and multilevel semantics while keeping the efficiency high.

Scene Parsing Segmentation +1

ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition

no code implementations5 Apr 2020 Qi Song, Qianyi Jiang, Nan Li, Rui Zhang, Xiaolin Wei

In this paper, we elaborately design a Rectified Attentional Double Supervised Network (ReADS) for general scene text recognition.

Scene Text Recognition valid

Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT

1 code implementation Radiology 2020 Lin Li, Lixin Qin, Zeguo Xu, Youbing Yin, Xin Wang, Bin Kong, Junjie Bai, Yi Lu, Zhenghan Fang, Qi Song, Kunlin Cao, Daliang Liu, Guisheng Wang, Qizhong Xu, Xisheng Fang, Shiqin Zhang, Juan Xia, Jun Xia

Materials and Methods In this retrospective and multi-center study, a deep learning model, COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT exams for the detection of COVID-19.

COVID-19 Image Segmentation Specificity

Category-wise Attack: Transferable Adversarial Examples for Anchor Free Object Detection

no code implementations10 Feb 2020 Quanyu Liao, Xin Wang, Bin Kong, Siwei Lyu, Youbing Yin, Qi Song, Xi Wu

Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbations can completely change the classification results.

Object object-detection +1

Domain Embedded Multi-model Generative Adversarial Networks for Image-based Face Inpainting

no code implementations5 Feb 2020 Xian Zhang, Xin Wang, Bin Kong, Youbing Yin, Qi Song, Siwei Lyu, Jiancheng Lv, Canghong Shi, Xiaojie Li

We firstly represent only face regions using the latent variable as the domain knowledge and combine it with the non-face parts textures to generate high-quality face images with plausible contents.

Facial Inpainting

DeepCenterline: a Multi-task Fully Convolutional Network for Centerline Extraction

no code implementations25 Mar 2019 Zhihui Guo, Junjie Bai, Yi Lu, Xin Wang, Kunlin Cao, Qi Song, Milan Sonka, Youbing Yin

The proposed method generates well-positioned centerlines, exhibiting lower number of missing branches and is more robust in the presence of minor imperfections of the object segmentation mask.

Object Semantic Segmentation

POI Semantic Model with a Deep Convolutional Structure

no code implementations18 Mar 2019 Ji Zhao, Meiyu Yu, Huan Chen, Boning Li, Lingyu Zhang, Qi Song, Li Ma, Hua Chai, Jieping Ye

An accurate similarity calculation is challenging since the mismatch between a query and a retrieval text may exist in the case of a mistyped query or an alias inquiry.

Retrieval

Attention-driven Tree-structured Convolutional LSTM for High Dimensional Data Understanding

no code implementations29 Jan 2019 Bin Kong, Xin Wang, Junjie Bai, Yi Lu, Feng Gao, Kunlin Cao, Qi Song, Shaoting Zhang, Siwei Lyu, Youbing Yin

In order to address these limitations, we present tree-structured ConvLSTM models for tree-structured image analysis tasks which can be trained end-to-end.

Vocal Bursts Intensity Prediction

Flow Based Self-supervised Pixel Embedding for Image Segmentation

no code implementations2 Jan 2019 Bin Ma, Shubao Liu, Yingxuan Zhi, Qi Song

Building on these, we demonstrate that image features can be learned in self-supervision by first training an optical flow estimator with synthetic flow data, and then learning image features from the estimated flows in real motion data.

Image Segmentation Optical Flow Estimation +2

Residual Attention based Network for Hand Bone Age Assessment

no code implementations21 Dec 2018 Eric Wu, Bin Kong, Xin Wang, Junjie Bai, Yi Lu, Feng Gao, Shaoting Zhang, Kunlin Cao, Qi Song, Siwei Lyu, Youbing Yin

The hierarchical attention components of the residual attention subnet force our network to focus on the key components of the X-ray images and generate the final predictions as well as the associated visual supports, which is similar to the assessment procedure of clinicians.

Hand Segmentation

Risk Stratification of Lung Nodules Using 3D CNN-Based Multi-task Learning

no code implementations28 Apr 2017 Sarfaraz Hussein, Kunlin Cao, Qi Song, Ulas Bagci

In order to address the need for a large amount for training data for CNN, we resort to transfer learning to obtain highly discriminative features.

Lung Cancer Diagnosis Multi-Task Learning

TumorNet: Lung Nodule Characterization Using Multi-View Convolutional Neural Network with Gaussian Process

no code implementations2 Mar 2017 Sarfaraz Hussein, Robert Gillies, Kunlin Cao, Qi Song, Ulas Bagci

Characterization of lung nodules as benign or malignant is one of the most important tasks in lung cancer diagnosis, staging and treatment planning.

Data Augmentation Lung Cancer Diagnosis

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