检索结果-内蒙古大学图书馆

Modality-aware triplet hard mining for zero-shot sketch-based image retrieval

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Huang, Zongheng Sun, Yifan Han, Chuchu Gao, Changxin Sang, Nong Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Baidu Research United States

This paper tackles the Zero-Shot Sketch-Based image Retrieval (ZS-SBIR) problem from the viewpoint of cross-modality metric learning. This task has two characteristics: 1) the zero-shot setting requires a metric space with good within-class compactness and the between-class discrepancy for recognizing the novel classes and 2) the sketch query and the photo gallery are in different modalities. The metric learning viewpoint benefits ZS-SBIR from two aspects. First, it facilitates improvement through recent good practices in deep metric learning (DML). By combining two fundamental learning approaches in DML, e.g., classification training and pairwise training, we set up a strong baseline for ZS-SBIR. Without bells and whistles, this baseline achieves competitive retrieval accuracy. Second, it provides an insight that properly suppressing the modality gap is critical. To this end, we design a novel method named Modality-Aware Triplet Hard Mining (MATHM). MATHM enhances the baseline with three types of pairwise learning, e.g., a cross-modality sample pair, a within-modality sample pair, and their combination. We also design an adaptive weighting method to balance these three components during training dynamically. Experimental results confirm that MATHM brings another round of significant improvement based on the strong baseline and sets up new state-of-the-art performance. For example, on the TU-Berlin dataset, we achieve 47.88+2.94% mAP@all and 58.28+2.34% Prec@100. Code will be publicly available. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

UniAnimate-DiT: Human image Animation with Large-Scale Video Diffusion Transformer

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Xiang Zhang, Shiwei Tang, Longxiang Zhang, Yingya Gao, Changxin Wang, Yuehuan Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology United States Alibaba Group China Tsinghua University China

This report presents UniAnimate-DiT, an advanced project that leverages the cutting-edge and powerful capabilities of the open-source Wan2.1 model for consistent human image animation. Specifically, to preserve the robust generative capabilities of the original Wan2.1 model, we implement Low-Rank Adaptation (LoRA) technique to fine-tune a minimal set of parameters, significantly reducing training memory overhead. A lightweight pose encoder consisting of multiple stacked 3D convolutional layers is designed to encode motion information of driving poses. Furthermore, we adopt a simple concatenation operation to integrate the reference appearance into the model and incorporate the pose information of the reference image for enhanced pose alignment. Experimental results show that our approach achieves visually appearing and temporally consistent high-fidelity animations. Trained on 480p (832x480) videos, UniAnimate-DiT demonstrates strong generalization capabilities to seamlessly upscale to 720P (1280x720) during inference. The training and inference code is publicly available at https://github. com/ali-vilab/UniAnimate-DiT. Copyright © 2025, The Authors. All rights reserved.

关键词：

Convergence analysis of nonconvex distributed stochastic zeroth-order coordinate method

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Shengjun Dong, Yunlong Xie, Dong Yao, Lisha Bailey, Colleen P. Fu, Shengli OSCAR Laboratory Department of Electrical Engineering University of North Texas DentonTX76207 United States School of Artificial Intelligence and Automation The MOE Key Laboratory of Image Processing and Intelligent Control The State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China

This paper investigates the stochastic distributed nonconvex optimization problem of minimizing a global cost function formed by the summation of n local cost functions. We solve such a problem by involving zeroth-order (ZO) information exchange. In this paper, we propose a ZO distributed primal–dual coordinate method (ZODIAC) to solve the stochastic optimization problem. Agents approximate their own local stochastic ZO oracle along with coordinates with an adaptive smoothing parameter. We show that the proposed algorithm achieves the convergence rate of O(√p/√T) for general nonconvex cost functions. We demonstrate the efficiency of proposed algorithms through a numerical example in comparison with the existing state-of-the-art centralized and distributed ZO algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Stochastic systems

Prognostic Prediction for Non-small-Cell Lung Cancer Based on Deep Neural Network and Multimodal Data 17th

学校读者我要写书评

暂无评论

Prognostic Prediction for Non-small-Cell Lung Cancer Based o...

17th International Conference on intelligent Computing, ICIC 2021

作者： Zhang, Zhong-Si Xu, Fei Jiang, Han-Jing Chen, Zhan-Heng Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University No. 4800 Caoan Road Shanghai201804 China

ISBN: (纸本)9783030845315

Non-small-cell lung cancer (NSCLC) is the most common lung cancer with poor prognosis. Prognostic prediction is significant in improving the prognosis of NSCLC patients. Clinical information and multi-omics data including gene expression, miRNA, copy number variations, and DNA methylation are closely related to NSCLC prognosis. In this study, we propose a deep neural network to conduct prognostic prediction for NSCLC patients based on all five types of data. Given the high dimensional features of the omics data, past works reduce the feature dimension by regression analysis or correlation sorting algorithms. A shortcoming of these methods is that only a small number of features are considered. To overcome it, we propose a convolution neural network-based feature transformation method, which considers all features and extracts the abstract representations of the omics data. Based on the representations, we predict the five-year survival status of NSCLC patients. The results show that our method achieves a more precise prediction than previous work, with the areas under the curve improved from 0.8163 to 0.8508 and the accuracy improved from 0.7544 to 0.8096. © 2021, Springer Nature Switzerland AG.

关键词： Forecasting

Prediction of Drug-Disease Associations Based on Long Short-Term Memory Network and Gaussian Interaction Profile Kernel 15th

学校读者我要写书评

暂无评论

Prediction of Drug-Disease Associations Based on Long Short-...

15th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2020

作者： Jiang, Han-Jing Wang, Yan-Bin Huang, Yabing Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China College of Computer Science and Technology Zhejiang University Hangzhou315000 China Department of Pathology Renmin Hospital of Wuhan University Wuhan430060 China

ISBN: (纸本)9789811613531

Drug-disease association depicts the accessibility landscape of the association at the molecular level, thereby revealing the intermolecular reaction in the process of drug reposition. However, the scarcity of drug-disease association data often complicates the drug reposition. In this work, we present a method for predicting drug-disease association, which is called drug-disease association prediction via Gaussian interaction profile kernel and long short-term memory network (G-LSTM). G-LSTM combines a recurrent network framework with a Gaussian interaction profile kernel to learn underlying features that accurately characterize drug-disease-association data. We have verified G-LSTM models on the two benchmark datasets Fdataset and Cdataset, respectively. The experimental results show that the predictive performance was significantly improved, with AUC of 0.9527 and 0.9705, respectively. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Long short-term memory

Exploiting Distilled Learning for Deep Siamese Tracking

学校读者我要写书评

暂无评论

Exploiting Distilled Learning for Deep Siamese Tracking

International Conference on Pattern Recognition

作者： Chengxin Liu Zhiguo Cao Wei Li Yang Xiao Shuaiyuan Du Angfan Zhu Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Queen Mary University of London

Existing deep siamese trackers are typically built on off-the-shelf CNN models for feature learning, with the demand for huge power consumption and memory storage. This limits current deep siamese trackers to be carried on resource-constrained devices like mobile phones, given factor that such a deployment normally requires cost-effective considerations. In this work, we address this issue by presenting a novel Distilled Learning Framework(DLF) for siamese tracking, which aims at learning tracking model with efficiency and high accuracy. Specifically, we propose two simple yet effective knowledge distillation strategies, denote as point-wise distillation and pairwise distillation, which are designed for transferring knowledge from a more discriminative teacher tracker into a compact student tracker. In this way, cost-effective and high performance tracking could be achieved. Extensive experiments on several tracking benchmarks demonstrate the effectiveness of our proposed method.

关键词： Power demand Pipelines Memory management Benchmark testing Mobile handsets Pattern recognition

A Stronger Baseline for Ego-Centric Action Detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qing, Zhiwu Huang, Ziyuan Wang, Xiang Feng, Yutong Zhang, Shiwei Jiang, Jianwen Tang, Mingqian Gao, Changxin Ang, Marcelo H. Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology ARC National University of Singapore Tsinghua University Alibaba Group

This technical report analyzes an egocentric video action detection method we used in the 2021 EPIC-KITCHENS-100 competition hosted in CVPR2021 Workshop. The goal of our task is to locate the start time and the end time of the action in the long untrimmed video, and predict action category. We adopt sliding window strategy to generate proposals, which can better adapt to short-duration actions. In addition, we show that classification and proposals are conflict in the same network. The separation of the two tasks boost the detection performance with high efficiency. By simply employing these strategy, we achieved 16.10% performance on the test set of EPIC-KITCHENS-100 Action Detection challenge using a single model, surpassing the baseline method by 11.7% in terms of average mAP. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Convergence Analysis of Nonconvex Distributed Stochastic Zeroth-order Coordinate Method

学校读者我要写书评

暂无评论

Convergence Analysis of Nonconvex Distributed Stochastic Zer...

IEEE Conference on Decision and control

作者： Shengjun Zhang Yunlong Dong Dong Xie Lisha Yao Colleen P. Bailey Shengli Fu OS-CAR Laboratory University of North Texas Denton TX USA School of Artificial Intelligence and Automation the MOE Key Laboratory of Image Processing and Intelligent Control and the State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan China University of North Texas Denton TX USA

ISBN: (纸本)9781665436601

This paper investigates the stochastic distributed nonconvex optimization problem of minimizing a global cost function formed by the summation of n local cost functions. We solve such a problem by involving zeroth-order (ZO) information exchange. In this paper, we propose a ZO distributed primal–dual coordinate method (ZODIAC) to solve the stochastic optimization problem. Agents approximate their own local stochastic ZO oracle along with coordinates under an adaptive smoothing parameter. We show that the proposed algorithm achieves the convergence rate of ${\mathcal{O}}(\sqrt p /\sqrt T )$ for general nonconvex cost functions. We demonstrate the efficiency of proposed algorithms through a numerical example in comparison with the existing state-of-the-art centralized and distributed ZO algorithms.

关键词： Smoothing methods Conferences Benchmark testing Cost function Approximation algorithms Information exchange Convergence

Attacking End-to-End Visual Navigation Model: How Weak Existing Learning-Based Approaches Can Be?

学校读者我要写书评

暂无评论

Attacking End-to-End Visual Navigation Model: How Weak Exist...

IEEE International Conference on Robotics and Biomimetics

作者： Hongye Wang Kefan Jin Hesheng Wang Shanghai Jiao Tong University China MOE Key Laboratory of Marine Intelligent Equipment and System State Key Laboratory of Ocean Engineering Shanghai Jiao Tong University China Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665405362

Learning-based self-driving techniques and vehicle navigation approaches are the most hot topics in recent years. However, existing approaches typically assume the attack-free sensor data, the safety issue under large disturbance or external attack have not been well-solved. In this article, we build a simple FGSM-based attack method designed by minimizing the maximum value of the extracted visual features in order to greatly decrease the performance of the popular learning model for vehicle navigation and even make it totally fail. The proposed min-max operation based feature space attack method solves the problems of branch activation uncertainties and the lack of labels. Furthermore, we also provide a general adversarial training framework which can be used to overcome the proposed feature space attack. Simulational experiments in CARLA platform demonstrate the effectiveness and practical applicability of our attacking approach and defence strategy.

关键词： Training Space vehicles Visualization Uncertainty Navigation Feature extraction Robustness