no code implementations • Findings (NAACL) 2022 • Yaqing Wang, Xin Tian, Haoyi Xiong, Yueyang Li, Zeyu Chen, Sheng Guo, Dejing Dou
In this work, we show that Relation Graph augmented Learning (RGL) can improve the performance of few-shot natural language understanding tasks.
no code implementations • 31 Mar 2025 • Miao Fan, Shanshan Yu, Shengtong Xu, Kun Jiang, Haoyi Xiong, Xiangzeng Liu
Autonomous driving faces safety challenges due to a lack of global perspective and the semantic information of vectorized high-definition (HD) maps.
no code implementations • 31 Mar 2025 • Miao Fan, Xuxu Kong, Shengtong Xu, Haoyi Xiong, Xiangzeng Liu
Real-time traffic light recognition is fundamental for autonomous driving safety and navigation in urban environments.
no code implementations • 31 Mar 2025 • Yi Yao, Miao Fan, Shengtong Xu, Haoyi Xiong, Xiangzeng Liu, WenBo Hu, Wenbing Huang
Lane topology reasoning techniques play a crucial role in high-definition (HD) mapping and autonomous driving applications.
no code implementations • 28 Mar 2025 • Shengyue Guan, Haoyi Xiong, Jindong Wang, Jiang Bian, Bin Zhu, Jian-Guang Lou
This survey examines evaluation methods for large language model (LLM)-based agents in multi-turn conversational settings.
no code implementations • 23 Mar 2025 • Xiaochen Zhang, Haoyi Xiong
In high-dimensional and high-stakes contexts, ensuring both rigorous statistical guarantees and interpretability in feature extraction from complex tabular data remains a formidable challenge.
no code implementations • 13 Mar 2025 • Tianhao Peng, Xuhong LI, Haitao Yuan, Yuchen Li, Haoyi Xiong
To preserve and enhance the unique characteristics inherent to subgraphs, a graph view generator optimizes augmentation strategies for each subgraph, thereby generating tailored views for graph contrastive learning.
no code implementations • 28 Jan 2025 • Xiaochen Zhang, Yunfeng Cai, Haoyi Xiong
Specifically, Knoop first generates multiple knockoff variables for each original variable and integrates them with the original variables into an over-parameterized Ridgeless regression model.
no code implementations • 23 Jan 2025 • Yuhui Yun, Huilong Ye, Xinru Li, Ruojia Li, Jingfeng Deng, Li Li, Haoyi Xiong
The paper introduces EICopilot, an novel agent-based solution enhancing search and exploration of enterprise registration data within extensive online knowledge graphs like those detailing legal entities, registered capital, and major shareholders.
no code implementations • 17 Dec 2024 • Zipeng Qi, Buhua Liu, Shiyan Zhang, Bao Li, Zhiqiang Xu, Haoyi Xiong, Zeke Xie
While recent zero-shot diffusion-based classifiers have made performance advancement on benchmark datasets, they still suffered badly from extremely slow classification speed (e. g., ~1000 seconds per classifying single image on ImageNet).
1 code implementation • 14 Dec 2024 • Lichen Bai, Shitong Shao, Zikai Zhou, Zipeng Qi, Zhiqiang Xu, Haoyi Xiong, Zeke Xie
Diffusion models, the most popular generative paradigm so far, can inject conditional information into the generation path to guide the latent towards desired directions.
no code implementations • 3 Nov 2024 • Tianhao Peng, Yuchen Li, Xuhong LI, Jiang Bian, Zeke Xie, Ning Sui, Shahid Mumtaz, Yanwu Xu, Linghe Kong, Haoyi Xiong
Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and predict molecular properties and activities, a critical step in fields like drug discovery and materials science.
1 code implementation • 5 Oct 2024 • Shitong Shao, Zikai Zhou, Lichen Bai, Haoyi Xiong, Zeke Xie
While there have been rapid advancements in developing inference-heavy algorithms for improved image generation, relatively little work has explored inference scaling laws in video diffusion models (VDMs).
no code implementations • 25 Sep 2024 • Yuchen Li, Haoyi Xiong, Linghe Kong, Zeyi Sun, Hongyang Chen, Shuaiqiang Wang, Dawei Yin
Both Transformer and Graph Neural Networks (GNNs) have been employed in the domain of learning to rank (LTR).
no code implementations • 25 Sep 2024 • Yuchen Li, Haoyi Xiong, Linghe Kong, Jiang Bian, Shuaiqiang Wang, Guihai Chen, Dawei Yin
Learning to rank (LTR) is widely employed in web searches to prioritize pertinent webpages from retrieved content based on input queries.
1 code implementation • 11 Sep 2024 • Buhua Liu, Shitong Shao, Bao Li, Lichen Bai, Zhiqiang Xu, Haoyi Xiong, James Kwok, Sumi Helal, Zeke Xie
Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications.
no code implementations • 21 Jul 2024 • Yuan Liao, Jiang Bian, Yuhui Yun, Shuo Wang, Yubo Zhang, Jiaming Chu, Tao Wang, Kewei Li, Yuchen Li, Xuhong LI, Shilei Ji, Haoyi Xiong
While the field of NL2SQL has made significant advancements in translating natural language instructions into executable SQL scripts for data querying and processing, achieving full automation within the broader data science pipeline - encompassing data querying, analysis, visualization, and reporting - remains a complex challenge.
no code implementations • 19 Jul 2024 • Zipeng Qi, Lichen Bai, Haoyi Xiong, Zeke Xie
We are the first to hypothesize and empirically observe that the generation quality of diffusion models significantly depend on the noise inversion stability.
no code implementations • 11 Jul 2024 • Haoyi Xiong, Zhiyuan Wang, Xuhong LI, Jiang Bian, Zeke Xie, Shahid Mumtaz, Anwer Al-Dulaimi, Laura E. Barnes
This article explores the convergence of connectionist and symbolic artificial intelligence (AI), from historical debates to contemporary advancements.
no code implementations • 28 Jun 2024 • Haoyi Xiong, Jiang Bian, Yuchen Li, Xuhong LI, Mengnan Du, Shuaiqiang Wang, Dawei Yin, Sumi Helal
Combining Large Language Models (LLMs) with search engine services marks a significant shift in the field of services computing, opening up new possibilities to enhance how we search for and retrieve information, understand content, and interact with internet services.
1 code implementation • 16 Jun 2024 • Song Zhang, Qingzhong Wang, Junyi Liu, Haoyi Xiong
Experiments demonstrate the effectiveness of our framework, showcasing its ability to generalize well across multiple tasks even under the scarcity of extensively annotated datasets, offering a scalable solution to automatic segmentation and annotation challenges in the field.
no code implementations • 24 Mar 2024 • Ruyi Yang, Jingyu Hu, Zihao Li, Jianli Mu, Tingzhao Yu, Jiangjiang Xia, Xuhong LI, Aritra Dasgupta, Haoyi Xiong
Advanced machine learning models have recently achieved high predictive accuracy for weather and climate prediction.
no code implementations • 16 Jan 2024 • Jiamin Chen, Xuhong LI, Yanwu Xu, Mengnan Du, Haoyi Xiong
Based on a large-scale medical image classification dataset, our work collects explanations from well-trained classifiers to generate pseudo labels of segmentation tasks.
no code implementations • 9 Jan 2024 • Haoyi Xiong, Xuhong LI, Xiaofei Zhang, Jiamin Chen, Xinhao Sun, Yuchen Li, Zeyi Sun, Mengnan Du
Given the complexity and lack of transparency in deep neural networks (DNNs), extensive efforts have been made to make these systems more interpretable or explain their behaviors in accessible terms.
no code implementations • 8 Nov 2023 • Yuehai Chen, Qingzhong Wang, Jing Yang, Badong Chen, Haoyi Xiong, Shaoyi Du
Crowd counting models in highly congested areas confront two main challenges: weak localization ability and difficulty in differentiating between foreground and background, leading to inaccurate estimations.
no code implementations • 6 Oct 2023 • Weibin Liao, Xuhong LI, Qingzhong Wang, Yanwu Xu, Zhaozheng Yin, Haoyi Xiong
While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on massive fine-annotated cell images [2] with bounding boxes, masks, and cell types for every cell in every image, to fine-tune the pre-trained model.
1 code implementation • 6 Oct 2023 • Song Zhang, Qingzhong Wang, Jiang Bian, Haoyi Xiong
While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the architecture and configuration, such as sampling the positional encoding, limiting their flexibility for various vision tasks.
no code implementations • 3 Oct 2023 • Weibin Liao, Haoyi Xiong, Qingzhong Wang, Yan Mo, Xuhong LI, Yi Liu, Zeyu Chen, Siyu Huang, Dejing Dou
In this work, we study a novel self-supervised pre-training pipeline, namely Multi-task Self-super-vised Continual Learning (MUSCLE), for multiple medical imaging tasks, such as classification and segmentation, using X-ray images collected from multiple body parts, including heads, lungs, and bones.
no code implementations • 24 Sep 2023 • Haoyi Xiong, Jiang Bian, Sijia Yang, Xiaofei Zhang, Linghe Kong, Daqing Zhang
Recently, with the rise of LLMs and their improved natural language understanding and reasoning capabilities, it has become feasible to model contexts using natural language and perform context reasoning by interacting with LLMs such as ChatGPT and GPT-4.
1 code implementation • 16 Apr 2023 • Wenke Xia, Xingjian Li, Andong Deng, Haoyi Xiong, Dejing Dou, Di Hu
However, such semantic consistency from the synchronization is hard to guarantee in unconstrained videos, due to the irrelevant modality noise and differentiated semantic correlation.
no code implementations • 1 Apr 2023 • Haoyi Xiong, Xuhong LI, Boyang Yu, Zhanxing Zhu, Dongrui Wu, Dejing Dou
While previous studies primarily focus on the affects of label noises to the performance of learning, our work intends to investigate the implicit regularization effects of the label noises, under mini-batch sampling settings of stochastic gradient descent (SGD), with assumptions that label noises are unbiased.
no code implementations • 24 Feb 2023 • Yuxuan Zhang, Qingzhong Wang, Jiang Bian, Yi Liu, Yanwu Xu, Dejing Dou, Haoyi Xiong
Due to the high similarity between MRI data and videos, we conduct extensive empirical studies on video recognition techniques for MRI classification to answer the questions: (1) can we directly use video recognition models for MRI classification, (2) which model is more appropriate for MRI, (3) are the common tricks like data augmentation in video recognition still useful for MRI classification?
1 code implementation • 5 Jan 2023 • Yan Li, Xinjiang Lu, Haoyi Xiong, Jian Tang, Jiantao Su, Bo Jin, Dejing Dou
Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning.
no code implementations • 20 Dec 2022 • Siyu Huang, Tianyang Wang, Haoyi Xiong, Bihan Wen, Jun Huan, Dejing Dou
Inspired by the fact that the samples with higher loss are usually more informative to the model than the samples with lower loss, in this paper we present a novel deep active learning approach that queries the oracle for data annotation when the unlabeled sample is believed to incorporate high loss.
1 code implementation • 19 Dec 2022 • Qingrui Jia, Xuhong LI, Lei Yu, Jiang Bian, Penghao Zhao, Shupeng Li, Haoyi Xiong, Dejing Dou
While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power.
no code implementations • 29 Nov 2022 • Junde Wu, Huihui Fang, Yehui Yang, Yu Zhang, Haoyi Xiong, Huazhu Fu, Yanwu Xu
In the paper, we call them expert-level classification.
2 code implementations • 1 Nov 2022 • Junde Wu, Rao Fu, Huihui Fang, Yu Zhang, Yehui Yang, Haoyi Xiong, Huiying Liu, Yanwu Xu
Inspired by the success of DPM, we propose the first DPM based model toward general medical image segmentation tasks, which we named MedSegDiff.
no code implementations • 20 Oct 2022 • Yuying Hao, Yi Liu, Juncai Peng, Haoyi Xiong, Guowei Chen, Shiyu Tang, Zeyu Chen, Baohua Lai
Interactive image segmentation aims at segmenting a target region through a way of human-computer interaction.
1 code implementation • 19 Sep 2022 • Nicholas Gray, Megan Moraes, Jiang Bian, Alex Wang, Allen Tian, Kurt Wilson, Yan Huang, Haoyi Xiong, Zhishan Guo
It provides an essential enrichment to the widely used LISA Traffic Sign dataset.
9 code implementations • 21 Aug 2022 • Ashkan Farhangi, Jiang Bian, Arthur Huang, Haoyi Xiong, Jun Wang, Zhishan Guo
Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner.
no code implementations • 26 Jul 2022 • Jiang Bian, Xuhong LI, Tao Wang, Qingzhong Wang, Jun Huang, Chen Liu, Jun Zhao, Feixiang Lu, Dejing Dou, Haoyi Xiong
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.
2 code implementations • 4 Jul 2022 • Xuhong LI, Haoyi Xiong, Yi Liu, Dingfu Zhou, Zeyu Chen, Yaqing Wang, Dejing Dou
Though image classification datasets could provide the backbone networks with rich visual features and discriminative ability, they are incapable of fully pre-training the target model (i. e., backbone+segmentation modules) in an end-to-end manner.
no code implementations • 4 Jul 2022 • Xueying Zhan, Zeyu Dai, Qingzhong Wang, Qing Li, Haoyi Xiong, Dejing Dou, Antoni B. Chan
In this paper, we propose a sampling scheme, Monte-Carlo Pareto Optimization for Active Learning (POAL), which selects optimal subsets of unlabeled samples with fixed batch size from the unlabeled data pool.
1 code implementation • 2 Jun 2022 • Fei Wu, Qingzhong Wang, Jian Bian, Haoyi Xiong, Ning Ding, Feixiang Lu, Jun Cheng, Dejing Dou
Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.
no code implementations • 20 May 2022 • Qingzhong Wang, Haifang Li, Haoyi Xiong, Wen Wang, Jiang Bian, Yu Lu, Shuaiqiang Wang, Zhicong Cheng, Dejing Dou, Dawei Yin
To handle the diverse query requests from users at web-scale, Baidu has done tremendous efforts in understanding users' queries, retrieve relevant contents from a pool of trillions of webpages, and rank the most relevant webpages on the top of results.
1 code implementation • 20 May 2022 • dianhai yu, Liang Shen, Hongxiang Hao, Weibao Gong, HuaChao Wu, Jiang Bian, LiRong Dai, Haoyi Xiong
For scalable inference in a single node, especially when the model size is larger than GPU memory, MoESys builds the CPU-GPU memory jointly into a ring of sections to load the model, and executes the computation tasks across the memory sections in a round-robin manner for efficient inference.
1 code implementation • 25 Mar 2022 • Xueying Zhan, Qingzhong Wang, Kuan-Hao Huang, Haoyi Xiong, Dejing Dou, Antoni B. Chan
In this work, We construct a DAL toolkit, DeepAL+, by re-implementing 19 highly-cited DAL methods.
no code implementations • ICCV 2023 • Andong Deng, Xingjian Li, Di Hu, Tianyang Wang, Haoyi Xiong, Chengzhong Xu
Based on the contradictory phenomenon between FE and FT that better feature extractor fails to be fine-tuned better accordingly, we conduct comprehensive analyses on features before softmax layer to provide insightful explanations.
1 code implementation • 14 Dec 2021 • Lutao Chu, Yi Liu, Zewu Wu, Shiyu Tang, Guowei Chen, Yuying Hao, Juncai Peng, Zhiliang Yu, Zeyu Chen, Baohua Lai, Haoyi Xiong
This work is the first to construct a large-scale video portrait dataset that contains 291 videos from 23 conference scenes with 14K fine-labeled frames and extensions to multi-camera teleconferencing.
no code implementations • 24 Oct 2021 • Kafeng Wang, Haoyi Xiong, Jie Zhang, Hongyang Chen, Dejing Dou, Cheng-Zhong Xu
Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i. e., 7 types by SenseMag versus 4 types by the existing work in comparisons).
no code implementations • 7 Oct 2021 • Haiyan Jiang, Haoyi Xiong, Dongrui Wu, Ji Liu, Dejing Dou
Principal component analysis (PCA) has been widely used as an effective technique for feature extraction and dimension reduction.
no code implementations • 6 Oct 2021 • Haoran Liu, Haoyi Xiong, Yaqing Wang, Haozhe An, Dongrui Wu, Dejing Dou
Specifically, we design a new metric $\mathcal{P}$-vector to represent the principal subspace of deep features learned in a DNN, and propose to measure angles between the principal subspaces using $\mathcal{P}$-vectors.
no code implementations • 29 Sep 2021 • Fan Wang, Hao Tian, Haoyi Xiong, Hua Wu, Yang Cao, Yu Kang, Haifeng Wang
While artificial neural networks (ANNs) have been widely adopted in machine learning, researchers are increasingly obsessed by the gaps between ANNs and natural neural networks (NNNs).
1 code implementation • 21 Sep 2021 • Yihang Yin, Qingzhong Wang, Siyu Huang, Haoyi Xiong, Xiang Zhang
Most of the existing contrastive learning methods employ pre-defined view generation methods, e. g., node drop or edge perturbation, which usually cannot adapt to input data or preserve the original semantic structures well.
2 code implementations • 8 Sep 2021 • Fan Wang, Hao Tian, Haoyi Xiong, Hua Wu, Jie Fu, Yang Cao, Yu Kang, Haifeng Wang
In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e. g., meta-learning.
no code implementations • 2 Sep 2021 • Xuhong LI, Haoyi Xiong, Siyu Huang, Shilei Ji, Dejing Dou
Existing interpretation algorithms have found that, even deep models make the same and right predictions on the same image, they might rely on different sets of input features for classification.
1 code implementation • ICCV 2021 • Siyu Huang, Tianyang Wang, Haoyi Xiong, Jun Huan, Dejing Dou
To lower the cost of data annotation, active learning has been proposed to interactively query an oracle to annotate a small proportion of informative samples in an unlabeled dataset.
1 code implementation • 21 Jul 2021 • Shuangli Li, Jingbo Zhou, Tong Xu, Liang Huang, Fan Wang, Haoyi Xiong, Weili Huang, Dejing Dou, Hui Xiong
To this end, we propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool).
Ranked #3 on
Protein-Ligand Affinity Prediction
on PDBbind
1 code implementation • 19 Jul 2021 • Qingzhong Wang, Pengfei Zhang, Haoyi Xiong, Jian Zhao
In this paper, we develop face. evoLVe -- a comprehensive library that collects and implements a wide range of popular deep learning-based methods for face recognition.
no code implementations • 2 Jul 2021 • Zhiyuan Wang, Haoyi Xiong, Jie Zhang, Sijia Yang, Mehdi Boukhechba, Laura E. Barnes, Daqing Zhang, Dejing Dou
Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals and provide timely intervention to promote health and well-beings, such as mental health and chronic cares.
no code implementations • 25 Jun 2021 • Haiyan Jiang, Shuyu Li, Luwei Zhang, Haoyi Xiong, Dejing Dou
Compared with existing algorithms, the proposed GRMF can automatically learn the grouping structure and sparsity in MF without prior knowledge, by introducing a naturally adjustable non-convex regularization to achieve simultaneous sparsity and grouping effect.
no code implementations • 20 Jun 2021 • Xuanyu Wu, Xuhong LI, Haoyi Xiong, Xiao Zhang, Siyu Huang, Dejing Dou
Incorporating with a set of randomized strategies for well-designed data transformations over the training set, ContRE adopts classification errors and Fisher ratios on the generated contrastive examples to assess and analyze the generalization performance of deep models in complement with a testing set.
1 code implementation • 3 Jun 2021 • Xiao Zhang, Dongrui Wu, Haoyi Xiong, Bo Dai
Unlike the conventional wisdom in statistical learning theory, the test error of a deep neural network (DNN) often demonstrates double descent: as the model complexity increases, it first follows a classical U-shaped curve and then shows a second descent.
1 code implementation • 3 Jun 2021 • Hao liu, Qian Gao, Jiang Li, Xiaochao Liao, Hao Xiong, Guangxing Chen, Wenlin Wang, Guobao Yang, Zhiwei Zha, daxiang dong, Dejing Dou, Haoyi Xiong
In this work, we present JIZHI - a Model-as-a-Service system - that per second handles hundreds of millions of online inference requests to huge deep models with more than trillions of sparse parameters, for over twenty real-time recommendation services at Baidu, Inc.
no code implementations • 29 Apr 2021 • Ji Liu, Jizhou Huang, Yang Zhou, Xuhong LI, Shilei Ji, Haoyi Xiong, Dejing Dou
Because of laws or regulations, the distributed data and computing resources cannot be directly shared among different regions or organizations for machine learning tasks.
no code implementations • 25 Mar 2021 • Xingjian Li, Haoyi Xiong, Chengzhong Xu, Dejing Dou
Performing mixup for transfer learning with pre-trained models however is not that simple, a high capacity pre-trained model with a large fully-connected (FC) layer could easily overfit to the target dataset even with samples-to-labels mixed up.
1 code implementation • 19 Mar 2021 • Xuhong LI, Haoyi Xiong, Xingjian Li, Xuanyu Wu, Xiao Zhang, Ji Liu, Jiang Bian, Dejing Dou
Then, to understand the interpretation results, we also survey the performance metrics for evaluating interpretation algorithms.
no code implementations • 1 Jan 2021 • Xuhong LI, Haoyi Xiong, Siyu Huang, Shilei Ji, Yanjie Fu, Dejing Dou
Given any task/dataset, Consensus first obtains the interpretation results using existing tools, e. g., LIME (Ribeiro et al., 2016), for every model in the committee, then aggregates the results from the entire committee and approximates the “ground truth” of interpretations through voting.
no code implementations • 1 Jan 2021 • Haoyi Xiong, Xuhong LI, Boyang Yu, Dejing Dou, Dongrui Wu, Zhanxing Zhu
Random label noises (or observational noises) widely exist in practical machinelearning settings.
no code implementations • 1 Jan 2021 • Haoran Liu, Haoyi Xiong, Yaqing Wang, Haozhe An, Dongrui Wu, Dejing Dou
While deep learning is effective to learn features/representations from data, the distributions of samples in feature spaces learned by various architectures for different training tasks (e. g., latent layers of AEs and feature vectors in CNN classifiers) have not been well-studied or compared.
no code implementations • 1 Jan 2021 • Haozhe An, Haoyi Xiong, Xuhong LI, Xingjian Li, Dejing Dou, Zhanxing Zhu
The recent theoretical investigation (Li et al., 2020) on the upper bound of generalization error of deep neural networks (DNNs) demonstrates the potential of using the gradient norm as a measure that complements validation accuracy for model selection in practice.
no code implementations • 22 Dec 2020 • Congxi Xiao, Jingbo Zhou, Jizhou Huang, An Zhuo, Ji Liu, Haoyi Xiong, Dejing Dou
Furthermore, to transfer the firsthand knowledge (witted in epicenters) to the target city before local outbreaks, we adopt a novel adversarial encoder framework to learn "city-invariant" representations from the mobility-related features for precise early detection of high-risk neighborhoods, even before any confirmed cases known, in the target city.
1 code implementation • 17 Dec 2020 • Jingbo Zhou, Shuangli Li, Liang Huang, Haoyi Xiong, Fan Wang, Tong Xu, Hui Xiong, Dejing Dou
The hierarchical attentive aggregation can capture spatial dependencies among atoms, as well as fuse the position-enhanced information with the capability of discriminating multiple spatial relations among atoms.
no code implementations • 16 Oct 2020 • Xingjian Li, Di Hu, Xuhong LI, Haoyi Xiong, Zhi Ye, Zhipeng Wang, Chengzhong Xu, Dejing Dou
Fine-tuning deep neural networks pre-trained on large scale datasets is one of the most practical transfer learning paradigm given limited quantity of training samples.
no code implementations • 20 Jul 2020 • Xingjian Li, Haoyi Xiong, Haozhe An, Cheng-Zhong Xu, Dejing Dou
While the existing multitask learning algorithms need to run backpropagation over both the source and target datasets and usually consume a higher gradient complexity, XMixup transfers the knowledge from source to target tasks more efficiently: for every class of the target task, XMixup selects the auxiliary samples from the source dataset and augments training samples via the simple mixup strategy.
1 code implementation • 17 Jul 2020 • Siyu Huang, Haoyi Xiong, Zhi-Qi Cheng, Qingzhong Wang, Xingran Zhou, Bihan Wen, Jun Huan, Dejing Dou
Generation of high-quality person images is challenging, due to the sophisticated entanglements among image factors, e. g., appearance, pose, foreground, background, local details, global structures, etc.
1 code implementation • ICML 2020 • Xingjian Li, Haoyi Xiong, Haozhe An, Cheng-Zhong Xu, Dejing Dou
RIFLE brings meaningful updates to the weights of deep CNN layers and improves low-level feature learning, while the effects of randomization can be easily converged throughout the overall learning procedure.
no code implementations • 6 May 2020 • Jizhou Huang, Haifeng Wang, Haoyi Xiong, Miao Fan, An Zhuo, Ying Li, Dejing Dou
While these strategies have effectively dealt with the critical situations of outbreaks, the combination of the pandemic and mobility controls has slowed China's economic growth, resulting in the first quarterly decline of Gross Domestic Product (GDP) since GDP began to be calculated, in 1992.
1 code implementation • 29 Apr 2020 • Xiao Zhang, Haoyi Xiong, Dongrui Wu
Over-parameterized deep neural networks (DNNs) with sufficient capacity to memorize random noise can achieve excellent generalization performance, challenging the bias-variance trade-off in classical learning theory.
no code implementations • 26 Apr 2020 • Xingjian Li, Haoyi Xiong, Haozhe An, Dejing Dou, Chengzhong Xu
Softening labels of training datasets with respect to data representations has been frequently used to improve the training of deep neural networks (DNNs).
1 code implementation • 17 Mar 2020 • Siyu Huang, Haoyi Xiong, Tianyang Wang, Bihan Wen, Qingzhong Wang, Zeyu Chen, Jun Huan, Dejing Dou
This paper further presents a real-time feed-forward model to leverage Style Projection for arbitrary image style transfer, which includes a regularization term for matching the semantics between input contents and stylized outputs.
no code implementations • 26 Jan 2020 • Di Hu, Zheng Wang, Haoyi Xiong, Dong Wang, Feiping Nie, Dejing Dou
Associating sound and its producer in complex audiovisual scene is a challenging task, especially when we are lack of annotated training data.
no code implementations • 5 Dec 2019 • Jie An, Haoyi Xiong, Jun Huan, Jiebo Luo
Our method consists of a construction step (C-step) to build a photorealistic stylization network and a pruning step (P-step) for acceleration.
no code implementations • 27 Nov 2019 • Zhi Fengy, Haoyi Xiong, Chuanyuan Song, Sijia Yang, Baoxin Zhao, Licheng Wang, Zeyu Chen, Shengwen Yang, Li-Ping Liu, Jun Huan
Our experiments using the real-world data showed that SecureGBM can well secure the communication and computation of LightGBM training and inference procedures for the both parties while only losing less than 3% AUC, using the same number of iterations for gradient boosting, on a wide range of benchmark datasets.
no code implementations • 18 Nov 2019 • Ruosi Wan, Haoyi Xiong, Xingjian Li, Zhanxing Zhu, Jun Huan
The empirical results show that the proposed descent direction estimation strategy DTNH can always improve the performance of deep transfer learning tasks based on all above regularizers, even when transferring pre-trained weights from inappropriate networks.
no code implementations • 6 Jul 2019 • Jie An, Haoyi Xiong, Jiebo Luo, Jun Huan, Jinwen Ma
Given a pair of images as the source of content and the reference of style, existing solutions usually first train an auto-encoder (AE) to reconstruct the image using deep features and then embeds pre-defined style transfer modules into the AE reconstruction procedure to transfer the style of the reconstructed image through modifying the deep features.
1 code implementation • ICML 2020 • Jingfeng Wu, Wenqing Hu, Haoyi Xiong, Jun Huan, Vladimir Braverman, Zhanxing Zhu
The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning.
no code implementations • 6 Jun 2019 • Jie An, Haoyi Xiong, Jinwen Ma, Jiebo Luo, Jun Huan
Finally compared to existing universal style transfer networks for photorealistic rendering such as PhotoWCT that stacks multiple well-trained auto-encoders and WCT transforms in a non-end-to-end manner, the architectures designed by StyleNAS produce better style-transferred images with details preserving, using a tiny number of operators/parameters, and enjoying around 500x inference time speed-up.
no code implementations • ICLR 2019 • Haoyi Xiong, Wenqing Hu, Zhanxing Zhu, Xinjian Li, Yunchao Zhang, Jun Huan
Derivative-free optimization (DFO) using trust region methods is frequently used for machine learning applications, such as (hyper-)parameter optimization without the derivatives of objective functions known.
2 code implementations • ICLR 2019 • Xingjian Li, Haoyi Xiong, Hanchao Wang, Yuxuan Rao, Li-Ping Liu, Zeyu Chen, Jun Huan
Instead of constraining the weights of neural network, DELTA aims to preserve the outer layer outputs of the target network.
no code implementations • 18 Jan 2019 • Wenqing Hu, Zhanxing Zhu, Haoyi Xiong, Jun Huan
We show in this case that the quasi-potential function is related to the noise covariance structure of SGD via a partial differential equation of Hamilton-Jacobi type.
no code implementations • 1 Jun 2018 • Ruosi Wan, Mingjun Zhong, Haoyi Xiong, Zhanxing Zhu
In statistics and machine learning, approximation of an intractable integration is often achieved by using the unbiased Monte Carlo estimator, but the variances of the estimation are generally high in many applications.
no code implementations • 15 Nov 2017 • Jiang Bian, Haoyi Xiong, Yanjie Fu, Sajal K. Das
In this paper, we present a novel community sensing paradigm -- {C}ommunity {S}ensing {W}ithout {A}ggregation}.
no code implementations • 25 Apr 2017 • Haoyi Xiong, Wei Cheng, Wenqing Hu, Jiang Bian, Zhishan Guo
Classical LDA for EHR data classification, however, suffers from two handicaps: the ill-posed estimation of LDA parameters (e. g., covariance matrix), and the "linear inseparability" of EHR data.
no code implementations • 18 Oct 2016 • Sijia Yang, Haoyi Xiong, Kaibo Xu, Licheng Wang, Jiang Bian, Zeyi Sun
In this paper, we revised the problem of predictive analysis of disease using personal EHR data and LDA classifier.
no code implementations • 22 Apr 2016 • Fereshteh Asgari, Alexis Sultan, Haoyi Xiong, Vincent Gauthier, Mounim El-Yacoubi
One of the main strengths of CT-Mapper is its capability to map noisy sparse cellular multimodal trajectories over a multilayer transportation network where the layers have different physical properties and not only to map trajectories associated with a single layer.