Search Results for author: Mingli Song

Found 73 papers, 32 papers with code

Collaboration by Competition: Self-coordinated Knowledge Amalgamation for Multi-talent Student Learning

no code implementations ECCV 2020 Sihui Luo, Wenwen Pan, Xinchao Wang, Dazhou Wang, Haihong Tang, Mingli Song

To this end, we propose a self-coordinate knowledge amalgamation network (SOKA-Net) for learning the multi-talent student model.

Topology-aware Generalization of Decentralized SGD

1 code implementation25 Jun 2022 Tongtian Zhu, Fengxiang He, Lan Zhang, Zhengyang Niu, Mingli Song, DaCheng Tao

This paper studies the algorithmic stability and generalizability of decentralized stochastic gradient descent (D-SGD).

Slimmable Domain Adaptation

2 code implementations CVPR 2022 Rang Meng, WeiJie Chen, Shicai Yang, Jie Song, Luojun Lin, Di Xie, ShiLiang Pu, Xinchao Wang, Mingli Song, Yueting Zhuang

In this paper, we introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank, from which models of different capacities can be sampled to accommodate different accuracy-efficiency trade-offs.

Domain Generalization Unsupervised Domain Adaptation

Label Matching Semi-Supervised Object Detection

2 code implementations CVPR 2022 Binbin Chen, WeiJie Chen, Shicai Yang, Yunyi Xuan, Jie Song, Di Xie, ShiLiang Pu, Mingli Song, Yueting Zhuang

To remedy this issue, we present a novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo labels to match each proposal in the student model accordingly.

object-detection Object Detection +1

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey

no code implementations22 May 2022 Gaoang Wang, Mingli Song, Jenq-Neng Hwang

Multi-object tracking (MOT) aims to associate target objects across video frames in order to obtain entire moving trajectories.

Image Classification Multi-Object Tracking +2

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

Comparison Knowledge Translation for Generalizable Image Classification

no code implementations7 May 2022 Zunlei Feng, Tian Qiu, Sai Wu, Xiaotuan Jin, Zengliang He, Mingli Song, Huiqiong Wang

In this paper, we attempt to build a generalizable framework that emulates the humans' recognition mechanism in the image classification task, hoping to improve the classification performance on unseen categories with the support of annotations of other categories.

Classification Image Classification +1

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 implementation CVPR 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 Object Detection

Imbalanced Sample Generation and Evaluation for Power System Transient Stability Using CTGAN

no code implementations16 Dec 2021 Gengshi Han, Shunyu Liu, KaiXuan Chen, Na Yu, Zunlei Feng, Mingli Song

This paper proposes a controllable sample generation framework based on Conditional Tabular Generative Adversarial Network (CTGAN) to generate specified transient stability samples.

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

Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training

1 code implementation CVPR 2022 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 +5

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

Learning Dynamic Preference Structure Embedding From Temporal Networks

1 code implementation23 Nov 2021 Tongya Zheng, Zunlei Feng, Yu Wang, Chengchao Shen, Mingli Song, Xingen Wang, Xinyu Wang, Chun Chen, Hao Xu

Our proposed Dynamic Preference Structure (DPS) framework consists of two stages: structure sampling and graph fusion.

Graph Sampling

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

Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks

no code implementations ICCV 2021 Yongcheng Jing, Yiding Yang, Xinchao Wang, Mingli Song, DaCheng Tao

In this paper, we study a novel meta aggregation scheme towards binarizing graph neural networks (GNNs).

Online Knowledge Distillation for Efficient Pose Estimation

no code implementations ICCV 2021 Zheng Li, Jingwen Ye, Mingli Song, Ying Huang, Zhigeng Pan

However, existing pose distillation works rely on a heavy pre-trained estimator to perform knowledge transfer and require a complex two-stage learning procedure.

Knowledge Distillation Pose Estimation +1

Edge-competing Pathological Liver Vessel Segmentation with Limited Labels

1 code implementation1 Aug 2021 Zunlei Feng, Zhonghua Wang, Xinchao Wang, Xiuming Zhang, Lechao Cheng, Jie Lei, Yuexuan Wang, Mingli Song

The diagnosis of MVI needs discovering the vessels that contain hepatocellular carcinoma cells and counting their number in each vessel, which depends heavily on experiences of the doctor, is largely subjective and time-consuming.

whole slide images

Boundary Knowledge Translation based Reference Semantic Segmentation

no code implementations1 Aug 2021 Lechao Cheng, Zunlei Feng, Xinchao Wang, Ya Jie Liu, Jie Lei, Mingli Song

In this paper, we introduce a novel Reference semantic segmentation Network (Ref-Net) to conduct visual boundary knowledge translation.

Semantic Segmentation Translation

Visual Boundary Knowledge Translation for Foreground Segmentation

1 code implementation1 Aug 2021 Zunlei Feng, Lechao Cheng, Xinchao Wang, Xiang Wang, Yajie Liu, Xiangtong Du, Mingli Song

To this end, we propose a Translation Segmentation Network (Trans-Net), which comprises a segmentation network and two boundary discriminators.

Semantic Segmentation Translation

Shape Controllable Virtual Try-on for Underwear Models

no code implementations28 Jul 2021 Xin Gao, Zhenjiang Liu, Zunlei Feng, Chengji Shen, Kairi Ou, Haihong Tang, Mingli Song

Existing 2D image-based virtual try-on methods aim to transfer a target clothing image onto a reference person, which has two main disadvantages: cannot control the size and length precisely; unable to accurately estimate the user's figure in the case of users wearing thick clothes, resulting in inaccurate dressing effect.

Graph Attention Virtual Try-on

Turning Frequency to Resolution: Video Super-Resolution via Event Cameras

no code implementations CVPR 2021 Yongcheng Jing, Yiding Yang, Xinchao Wang, Mingli Song, DaCheng Tao

To this end, we propose an Event-based VSR framework (E-VSR), of which the key component is an asynchronous interpolation (EAI) module that reconstructs a high-frequency (HF) video stream with uniform and tiny pixel displacements between neighboring frames from an event stream.

Video Super-Resolution

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

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

SPAGAN: Shortest Path Graph Attention Network

1 code implementation10 Jan 2021 Yiding Yang, Xinchao Wang, Mingli Song, Junsong Yuan, DaCheng Tao

SPAGAN therefore allows for a more informative and intact exploration of the graph structure and further {a} more effective aggregation of information from distant neighbors into the center node, as compared to node-based GCN methods.

Graph Attention

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

One-sample Guided Object Representation Disassembling

no code implementations NeurIPS 2020 Zunlei Feng, Yongming He, Xinchao Wang, Xin Gao, Jie Lei, Cheng Jin, Mingli Song

In this paper, we introduce the One-sample Guided Object Representation Disassembling (One-GORD) method, which only requires one annotated sample for each object category to learn disassembled object representation from unannotated images.

Data Augmentation Image Classification

DEAL: Difficulty-aware Active Learning for Semantic Segmentation

1 code implementation17 Oct 2020 Shuai Xie, Zunlei Feng, Ying Chen, Songtao Sun, Chao Ma, Mingli Song

To deal with this problem, we propose a semantic Difficulty-awarE Active Learning (DEAL) network composed of two branches: the common segmentation branch and the semantic difficulty branch.

Active Learning Semantic Segmentation

Learning Propagation Rules for Attribution Map Generation

no code implementations ECCV 2020 Yiding Yang, Jiayan Qiu, Mingli Song, DaCheng Tao, Xinchao Wang

Prior gradient-based attribution-map methods rely on handcrafted propagation rules for the non-linear/activation layers during the backward pass, so as to produce gradients of the input and then the attribution map.

Factorizable Graph Convolutional Networks

1 code implementation NeurIPS 2020 Yiding Yang, Zunlei Feng, Mingli Song, Xinchao Wang

In this paper, we introduce a novel graph convolutional network (GCN), termed as factorizable graph convolutional network(FactorGCN), that explicitly disentangles such intertwined relations encoded in a graph.

Graph Classification Graph Regression +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

Disassembling Object Representations without Labels

no code implementations3 Apr 2020 Zunlei Feng, Xinchao Wang, Yongming He, Yike Yuan, Xin Gao, Mingli Song

In this paper, we study a new representation-learning task, which we termed as disassembling object representations.

General Classification Representation Learning +1

Distilling Knowledge from Graph Convolutional Networks

1 code implementation CVPR 2020 Yiding Yang, Jiayan Qiu, Mingli Song, DaCheng Tao, Xinchao Wang

To enable the knowledge transfer from the teacher GCN to the student, we propose a local structure preserving module that explicitly accounts for the topological semantics of the teacher.

Knowledge Distillation Transfer Learning

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

Semantic Regularization: Improve Few-shot Image Classification by Reducing Meta Shift

no code implementations18 Dec 2019 Da Chen, Yong-Liang Yang, Zunlei Feng, Xiang Wu, Mingli Song, Wenbin Li, Yuan He, Hui Xue, Feng Mao

This strategy leads to severe meta shift issues across multiple tasks, meaning the learned prototypes or class descriptors are not stable as each task only involves their own support set.

Few-Shot Image Classification General Classification +1

Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers

no code implementations26 Nov 2019 Ya Zhao, Rui Xu, Xinchao Wang, Peng Hou, Haihong Tang, Mingli Song

In this paper, we propose a new method, termed as Lip by Speech (LIBS), of which the goal is to strengthen lip reading by learning from speech recognizers.

 Ranked #1 on Lipreading on CMLR

Knowledge Distillation Lipreading +2

Dynamic Instance Normalization for Arbitrary Style Transfer

no code implementations16 Nov 2019 Yongcheng Jing, Xiao Liu, Yukang Ding, Xinchao Wang, Errui Ding, Mingli Song, Shilei Wen

Prior normalization methods rely on affine transformations to produce arbitrary image style transfers, of which the parameters are computed in a pre-defined way.

Style Transfer

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.

A Cascade Sequence-to-Sequence Model for Chinese Mandarin Lip Reading

no code implementations14 Aug 2019 Ya Zhao, Rui Xu, Mingli Song

When trained on CMLR dataset, the proposed CSSMCM surpasses the performance of state-of-the-art lip reading frameworks, which confirms the effectiveness of explicit modeling of tones for Chinese Mandarin lip reading.

Lipreading Lip Reading

Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning

2 code implementations24 Jun 2019 Sihui Luo, Xinchao Wang, Gongfan Fang, Yao Hu, Dapeng Tao, Mingli Song

An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations.

Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers

1 code implementation28 May 2019 Jingwen Ye, Xinchao Wang, Yixin Ji, Kairi Ou, Mingli Song

Many well-trained Convolutional Neural Network(CNN) models have now been released online by developers for the sake of effortless reproducing.

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

Interpretable Partitioned Embedding for Customized Fashion Outfit Composition

no code implementations13 Jun 2018 Zunlei Feng, Zhenyun Yu, Yezhou Yang, Yongcheng Jing, Junxiao Jiang, Mingli Song

In the supervised attributes module, multiple attributes labels are adopted to ensure that different parts of the overall embedding correspond to different attributes.

Dual Swap Disentangling

1 code implementation NeurIPS 2018 Zunlei Feng, Xinchao Wang, Chenglong Ke, An-Xiang Zeng, DaCheng Tao, Mingli Song

To achieve disentangling using the labeled pairs, we follow a "encoding-swap-decoding" process, where we first swap the parts of their encodings corresponding to the shared attribute and then decode the obtained hybrid codes to reconstruct the original input pairs.

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

Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields

1 code implementation ECCV 2018 Yongcheng Jing, Yang Liu, Yezhou Yang, Zunlei Feng, Yizhou Yu, DaCheng Tao, Mingli Song

In this paper, we present a stroke controllable style transfer network that can achieve continuous and spatial stroke size control.

Style Transfer

DeepSIC: Deep Semantic Image Compression

no code implementations29 Jan 2018 Sihui Luo, Yezhou Yang, Mingli Song

The same practice also enable the compressed code to carry the image semantic information during storage and transmission.

Image Compression Object Recognition

TripletGAN: Training Generative Model with Triplet Loss

no code implementations14 Nov 2017 Gongze Cao, Yezhou Yang, Jie Lei, Cheng Jin, Yang Liu, Mingli Song

As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts.

Face Recognition General Classification +1

Neural Style Transfer: A Review

7 code implementations11 May 2017 Yongcheng Jing, Yezhou Yang, Zunlei Feng, Jingwen Ye, Yizhou Yu, Mingli Song

We first propose a taxonomy of current algorithms in the field of NST.

Style Transfer

Semi-Supervised Coupled Dictionary Learning for Person Re-identification

no code implementations CVPR 2014 Xiao Liu, Mingli Song, DaCheng Tao, Xingchen Zhou, Chun Chen, Jiajun Bu

In this paper, to bridge the human appearance variations across cameras, two coupled dictionaries that relate to the gallery and probe cameras are jointly learned in the training phase from both labeled and unlabeled images.

Dictionary Learning Person Re-Identification

Probabilistic Graphlet Cut: Exploiting Spatial Structure Cue for Weakly Supervised Image Segmentation

no code implementations CVPR 2013 Luming Zhang, Mingli Song, Zicheng Liu, Xiao Liu, Jiajun Bu, Chun Chen

Finally, we propose a novel image segmentation algorithm, called graphlet cut, that leverages the learned graphlet distribution in measuring the homogeneity of a set of spatially structured superpixels.

Semantic Segmentation Superpixels

Sparse Norm Filtering

no code implementations17 May 2013 Chengxi Ye, DaCheng Tao, Mingli Song, David W. Jacobs, Min Wu

Optimization-based filtering smoothes an image by minimizing a fidelity function and simultaneously preserves edges by exploiting a sparse norm penalty over gradients.

Colorization Deblurring +1

Spectral Graph Cut from a Filtering Point of View

no code implementations20 May 2012 Chengxi Ye, Yuxu Lin, Mingli Song, Chun Chen, David W. Jacobs

In this paper, we analyze image segmentation algorithms that are based on spectral graph theory, e. g., normalized cut, and show that there is a natural connection between spectural graph theory based image segmentationand and edge preserving filtering.

Semantic Segmentation

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