Search Results for author: Jie Song

Found 51 papers, 19 papers with code

Distribution-Aware Graph Representation Learning for Transient Stability Assessment of Power System

no code implementations12 May 2022 KaiXuan Chen, Shunyu Liu, Na Yu, Rong Yan, Quan Zhang, Jie Song, Zunlei Feng, Mingli Song

As the topology of the power system is in the form of graph structure, graph neural network based representation learning is naturally suitable for learning the status of the power system.

Graph Representation Learning Numerical Integration

Spot-adaptive Knowledge Distillation

1 code implementation5 May 2022 Jie Song, Ying Chen, Jingwen Ye, Mingli Song

Knowledge distillation (KD) has become a well established paradigm for compressing deep neural networks.

Knowledge Distillation

Meta-attention for ViT-backed Continual Learning

1 code implementation22 Mar 2022 Mengqi Xue, Haofei Zhang, Jie Song, Mingli Song

Continual learning is a longstanding research topic due to its crucial role in tackling continually arriving tasks.

Continual Learning

Knowledge Amalgamation for Object Detection with Transformers

no code implementations7 Mar 2022 Haofei Zhang, Feng Mao, Mengqi Xue, Gongfan Fang, Zunlei Feng, Jie Song, Mingli Song

Moreover, the transformer-based students excel in learning amalgamated knowledge, as they have mastered heterogeneous detection tasks rapidly and achieved superior or at least comparable performance to those of the teachers in their specializations.

Object Detection

PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence

no code implementations3 Mar 2022 Zijian Dong, Chen Guo, Jie Song, Xu Chen, Andreas Geiger, Otmar Hilliges

We present a novel method to learn Personalized Implicit Neural Avatars (PINA) from a short RGB-D sequence.

Frame

Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN

no code implementations17 Jan 2022 Jie Song, Huawei Yi, Wenqian Xu, Xiaohui Li, Bo Li, Yuanyuan Liu

The proposal of perceptual loss solves the problem that per-pixel difference loss function causes the reconstructed image to be overly-smooth, which acquires a significant progress in the field of single image super-resolution reconstruction.

Image Super-Resolution

gDNA: Towards Generative Detailed Neural Avatars

no code implementations11 Jan 2022 Xu Chen, Tianjian Jiang, Jie Song, Jinlong Yang, Michael J. Black, Andreas Geiger, Otmar Hilliges

Furthermore, we show that our method can be used on the task of fitting human models to raw scans, outperforming the previous state-of-the-art.

Up to 100$\times$ Faster Data-free Knowledge Distillation

1 code implementation12 Dec 2021 Gongfan Fang, Kanya Mo, Xinchao Wang, Jie Song, Shitao Bei, Haofei Zhang, Mingli Song

At the heart of our approach is a novel strategy to reuse the shared common features in training data so as to synthesize different data instances.

Knowledge Distillation

Auto-Tag: Tagging-Data-By-Example in Data Lakes

no code implementations11 Dec 2021 Yeye He, Jie Song, Yue Wang, Surajit Chaudhuri, Vishal Anil, Blake Lassiter, Yaron Goland, Gaurav Malhotra

As data lakes become increasingly popular in large enterprises today, there is a growing need to tag or classify data assets (e. g., files and databases) in data lakes with additional metadata (e. g., semantic column-types), as the inferred metadata can enable a range of downstream applications like data governance (e. g., GDPR compliance), and dataset search.

TAG

Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training

1 code implementation7 Dec 2021 Haofei Zhang, Jiarui Duan, Mengqi Xue, Jie Song, Li Sun, Mingli Song

Recently, vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in the realm of computer vision (CV).

A Survey of Deep Learning for Low-Shot Object Detection

no code implementations6 Dec 2021 Qihan Huang, Haofei Zhang, Mengqi Xue, Jie Song, Mingli Song

Although few-shot learning and zero-shot learning have been extensively explored in the field of image classification, it is indispensable to design new methods for object detection in the data-scarce scenario since object detection has an additional challenging localization task.

Few-Shot Learning Few-Shot Object Detection +4

Safe Distillation Box

no code implementations5 Dec 2021 Jingwen Ye, Yining Mao, Jie Song, Xinchao Wang, Cheng Jin, Mingli Song

In other words, all users may employ a model in SDB for inference, but only authorized users get access to KD from the model.

Knowledge Distillation

D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions

no code implementations1 Dec 2021 Sammy Christen, Muhammed Kocabas, Emre Aksan, Jemin Hwangbo, Jie Song, Otmar Hilliges

We introduce the dynamic grasp synthesis task: given an object with a known 6D pose and a grasp reference, our goal is to generate motions that move the object to a target 6D pose.

motion synthesis

Human Performance Capture from Monocular Video in the Wild

no code implementations29 Nov 2021 Chen Guo, Xu Chen, Jie Song, Otmar Hilliges

In this work, we propose a method capable of capturing the dynamic 3D human shape from a monocular video featuring challenging body poses, without any additional input.

Autonomous Driving

Render In-between: Motion Guided Video Synthesis for Action Interpolation

no code implementations1 Nov 2021 Hsuan-I Ho, Xu Chen, Jie Song, Otmar Hilliges

We propose to address these issues in a motion-guided frame-upsampling framework that is capable of producing realistic human motion and appearance.

Frame Neural Rendering

Shape-aware Multi-Person Pose Estimation from Multi-View Images

no code implementations ICCV 2021 Zijian Dong, Jie Song, Xu Chen, Chen Guo, Otmar Hilliges

In this paper we contribute a simple yet effective approach for estimating 3D poses of multiple people from multi-view images.

Multi-Person Pose Estimation

Distribution Knowledge Embedding for Graph Pooling

no code implementations29 Sep 2021 KaiXuan Chen, Jie Song, Shunyu Liu, Na Yu, Zunlei Feng, Gengshi Han, Mingli Song

A DKEPool network de facto disassembles representation learning into two stages, structure learning and distribution learning.

Representation Learning

Tree-Like Decision Distillation

no code implementations CVPR 2021 Jie Song, Haofei Zhang, Xinchao Wang, Mengqi Xue, Ying Chen, Li Sun, DaCheng Tao, Mingli Song

Knowledge distillation pursues a diminutive yet well-behaved student network by harnessing the knowledge learned by a cumbersome teacher model.

Decision Making Knowledge Distillation

Contrastive Model Inversion for Data-Free Knowledge Distillation

1 code implementation18 May 2021 Gongfan Fang, Jie Song, Xinchao Wang, Chengchao Shen, Xingen Wang, Mingli Song

In this paper, we propose Contrastive Model Inversion~(CMI), where the data diversity is explicitly modeled as an optimizable objective, to alleviate the mode collapse issue.

Contrastive Learning Knowledge Distillation

Auto-Validate: Unsupervised Data Validation Using Data-Domain Patterns Inferred from Data Lakes

no code implementations10 Apr 2021 Jie Song, Yeye He

Complex data pipelines are increasingly common in diverse applications such as BI reporting and ML modeling.

TAG

DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Network

no code implementations15 Mar 2021 Yang Liu, Tu Zheng, Jie Song, Deng Cai, Xiaofei He

In this paper, we argue that a Mutual Nearest Neighbor (MNN) relation should be established to explicitly select the query descriptors that are most relevant to each task and discard less relevant ones from aggregative clutters in FSL.

Few-Shot Learning

Data-Driven Short-Term Voltage Stability Assessment Based on Spatial-Temporal Graph Convolutional Network

no code implementations5 Mar 2021 Yonghong Luo, Chao Lu, Lipeng Zhu, Jie Song

The proposed STGCN utilizes graph convolution to integrate network topology information into the learning model to exploit spatial information.

Training Generative Adversarial Networks in One Stage

1 code implementation CVPR 2021 Chengchao Shen, Youtan Yin, Xinchao Wang, Xubin Li, Jie Song, Mingli Song

Based on the adversarial losses of the generator and discriminator, we categorize GANs into two classes, Symmetric GANs and Asymmetric GANs, and introduce a novel gradient decomposition method to unify the two, allowing us to train both classes in one stage and hence alleviate the training effort.

Image Generation Knowledge Distillation

Self-Born Wiring for Neural Trees

no code implementations ICCV 2021 Ying Chen, Feng Mao, Jie Song, Xinchao Wang, Huiqiong Wang, Mingli Song

Neural trees aim at integrating deep neural networks and decision trees so as to bring the best of the two worlds, including representation learning from the former and faster inference from the latter.

Representation Learning

Progressive Network Grafting for Few-Shot Knowledge Distillation

1 code implementation9 Dec 2020 Chengchao Shen, Xinchao Wang, Youtan Yin, Jie Song, Sihui Luo, Mingli Song

In this paper, we investigate the practical few-shot knowledge distillation scenario, where we assume only a few samples without human annotations are available for each category.

Knowledge Distillation Model Compression +1

Convolutional Autoencoders for Human Motion Infilling

1 code implementation22 Oct 2020 Manuel Kaufmann, Emre Aksan, Jie Song, Fabrizio Pece, Remo Ziegler, Otmar Hilliges

At the heart of our approach lies the idea to cast motion infilling as an inpainting problem and to train a convolutional de-noising autoencoder on image-like representations of motion sequences.

Human Body Model Fitting by Learned Gradient Descent

no code implementations ECCV 2020 Jie Song, Xu Chen, Otmar Hilliges

We propose a novel algorithm for the fitting of 3D human shape to images.

Category Level Object Pose Estimation via Neural Analysis-by-Synthesis

no code implementations ECCV 2020 Xu Chen, Zijian Dong, Jie Song, Andreas Geiger, Otmar Hilliges

Many object pose estimation algorithms rely on the analysis-by-synthesis framework which requires explicit representations of individual object instances.

Image Generation Pose Estimation

Sparse Coding Driven Deep Decision Tree Ensembles for Nuclear Segmentation in Digital Pathology Images

no code implementations13 Aug 2020 Jie Song, Liang Xiao, Mohsen Molaei, Zhichao Lian

In this way, rich image appearance models together with more contextual information are integrated by learning a series of decision tree ensembles.

Nuclear Segmentation Representation Learning +1

Impression Space from Deep Template Network

no code implementations10 Jul 2020 Gongfan Fang, Xinchao Wang, Haofei Zhang, Jie Song, Mingli Song

This network is referred to as the {\emph{Template Network}} because its filters will be used as templates to reconstruct images from the impression.

Image Generation Translation

DEPARA: Deep Attribution Graph for Deep Knowledge Transferability

1 code implementation CVPR 2020 Jie Song, Yixin Chen, Jingwen Ye, Xinchao Wang, Chengchao Shen, Feng Mao, Mingli Song

In this paper, we propose the DEeP Attribution gRAph (DEPARA) to investigate the transferability of knowledge learned from PR-DNNs.

Model Selection Transfer Learning

Data-Free Adversarial Distillation

2 code implementations23 Dec 2019 Gongfan Fang, Jie Song, Chengchao Shen, Xinchao Wang, Da Chen, Mingli Song

Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer.

Knowledge Distillation Model Compression +2

Deep Model Transferability from Attribution Maps

1 code implementation NeurIPS 2019 Jie Song, Yixin Chen, Xinchao Wang, Chengchao Shen, Mingli Song

Exploring the transferability between heterogeneous tasks sheds light on their intrinsic interconnections, and consequently enables knowledge transfer from one task to another so as to reduce the training effort of the latter.

Transfer Learning

Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation

1 code implementation ICCV 2019 Chengchao Shen, Mengqi Xue, Xinchao Wang, Jie Song, Li Sun, Mingli Song

To this end, we introduce a dual-step strategy that first extracts the task-specific knowledge from the heterogeneous teachers sharing the same sub-task, and then amalgamates the extracted knowledge to build the student network.

Investigation of wind pressures on tall building under interference effects using machine learning techniques

no code implementations20 Aug 2019 Gang Hu, Lingbo Liu, DaCheng Tao, Jie Song, K. C. S. Kwok

This study used machine learning techniques to resolve the conflicting requirement between limited wind tunnel tests that produce unreliable results and a completed investigation of the interference effects that is costly and time-consuming.

Unpaired Pose Guided Human Image Generation

1 code implementation8 Jan 2019 Xu Chen, Jie Song, Otmar Hilliges

This paper studies the task of full generative modelling of realistic images of humans, guided only by coarse sketch of the pose, while providing control over the specific instance or type of outfit worn by the user.

Image-to-Image Translation Translation

Monocular Neural Image Based Rendering with Continuous View Control

2 code implementations ICCV 2019 Xu Chen, Jie Song, Otmar Hilliges

The approach is self-supervised and only requires 2D images and associated view transforms for training.

Novel View Synthesis

End-to-end Learning for Graph Decomposition

no code implementations ICCV 2019 Jie Song, Bjoern Andres, Michael Black, Otmar Hilliges, Siyu Tang

The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels of the initial graph and the hard constraints are introduced in the CRF as high-order potentials.

Multi-Person Pose Estimation

Amalgamating Knowledge towards Comprehensive Classification

1 code implementation7 Nov 2018 Chengchao Shen, Xinchao Wang, Jie Song, Li Sun, Mingli Song

We propose in this paper to study a new model-reusing task, which we term as \emph{knowledge amalgamation}.

Classification General Classification

Transductive Unbiased Embedding for Zero-Shot Learning

no code implementations CVPR 2018 Jie Song, Chengchao Shen, Yezhou Yang, Yang Liu, Mingli Song

Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes.

Zero-Shot Learning

Cross-modal Deep Variational Hand Pose Estimation

1 code implementation CVPR 2018 Adrian Spurr, Jie Song, Seonwook Park, Otmar Hilliges

Furthermore, we show that our proposed method can be used without changes on depth images and performs comparably to specialized methods.

Hand Pose Estimation

Learning Human Motion Models for Long-term Predictions

no code implementations10 Apr 2017 Partha Ghosh, Jie Song, Emre Aksan, Otmar Hilliges

Furthermore, we propose new evaluation protocols to assess the quality of synthetic motion sequences even for which no ground truth data exists.

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