528 citations · 783 across the 27 of their papers we have counts for
27 papers
Dense Affinity Matching for Few-Shot Segmentation
Hao Chen, Yonghan Dong, Zheming Lu +4
Few-Shot Segmentation (FSS) aims to segment the novel class images with a few annotated samples. In this paper, we propose a dense affinity matching (DAM) framework to exploit the…
Stable Prediction on Graphs with Agnostic Distribution Shift
Shengyu Zhang, Kun Kuang, Jiezhong Qiu +5
Graph is a flexible and effective tool to represent complex structures in practice and graph neural networks (GNNs) have been shown to be effective on various graph tasks with rand…
Self-Taught Cross-Domain Few-Shot Learning with Weakly Supervised Object Localization and Task-Decomposition
Xiyao Liu, Zhong Ji, Yanwei Pang +1
The domain shift between the source and target domain is the main challenge in Cross-Domain Few-Shot Learning (CD-FSL). However, the target domain is absolutely unknown during the…
Graph-Free Knowledge Distillation for Graph Neural Networks
Xiang Deng, Zhongfei Zhang
Knowledge distillation (KD) transfers knowledge from a teacher network to a student by enforcing the student to mimic the outputs of the pretrained teacher on training data. Howeve…
Learning with Retrospection
Xiang Deng, Zhongfei Zhang
Deep neural networks have been successfully deployed in various domains of artificial intelligence, including computer vision and natural language processing. We observe that the c…
CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
Xingran Zhou, Bo Zhang, Ting Zhang +5
We present the full-resolution correspondence learning for cross-domain images, which aids image translation. We adopt a hierarchical strategy that uses the correspondence from coa…
Deep Metric Learning with Spherical Embedding
Dingyi Zhang, Yingming Li, Zhongfei Zhang
Deep metric learning has attracted much attention in recent years, due to seamlessly combining the distance metric learning and deep neural network. Many endeavors are devoted to d…
Locally Linear Region Knowledge Distillation
Xiang Deng, Zhongfei, Zhang
Knowledge distillation (KD) is an effective technique to transfer knowledge from one neural network (teacher) to another (student), thus improving the performance of the student. T…
Deep Collective Learning: Learning Optimal Inputs and Weights Jointly in Deep Neural Networks
Xiang Deng, Zhongfei, Zhang
It is well observed that in deep learning and computer vision literature, visual data are always represented in a manually designed coding scheme (eg., RGB images are represented a…
Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?
Xiang Deng, Zhongfei Zhang
Substantial efforts have been made on improving the generalization abilities of deep neural networks (DNNs) in order to obtain better performances without introducing more paramete…
Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
Tao Jin, Siyu Huang, Yingming Li +1
This paper addresses the challenging task of video captioning which aims to generate descriptions for video data. Recently, the attention-based encoder-decoder structures have been…
A Semantics-Guided Class Imbalance Learning Model for Zero-Shot Classification
Zhong Ji, Xuejie Yu, Yunlong Yu +2
Zero-Shot Classification (ZSC) equips the learned model with the ability to recognize the visual instances from the novel classes via constructing the interactions between the visu…
Text Guided Person Image Synthesis
Xingran Zhou, Siyu Huang, Bin Li +3
This paper presents a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions. Our method can be boiled d…
Cross-relation Cross-bag Attention for Distantly-supervised Relation Extraction
Yujin Yuan, Liyuan Liu, Siliang Tang +5
Distant supervision leverages knowledge bases to automatically label instances, thus allowing us to train relation extractor without human annotations. However, the generated train…
Bi-Adversarial Auto-Encoder for Zero-Shot Learning
Yunlong Yu, Zhong Ji, Yanwei Pang +3
Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from th…
Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learning
Yunlong Yu, Zhong Ji, Yanwei Fu +3
Zero-Shot Learning (ZSL) is achieved via aligning the semantic relationships between the global image feature vector and the corresponding class semantic descriptions. However, usi…
GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
Siyu Huang, Xi Li, Zhi-Qi Cheng +2
A key problem in deep multi-attribute learning is to effectively discover the inter-attribute correlation structures. Typically, the conventional deep multi-attribute learning appr…
Pyramid Person Matching Network for Person Re-identification
Chaojie Mao, Yingming Li, Zhongfei Zhang +2
In this work, we present a deep convolutional pyramid person matching network (PPMN) with specially designed Pyramid Matching Module to address the problem of person re-identificat…
A Deep Learning Approach for Expert Identification in Question Answering Communities
Chen Zheng, Shuangfei Zhai, Zhongfei Zhang
In this paper, we describe an effective convolutional neural network framework for identifying the expert in question answering community. This approach uses the convolutional neur…
Text Coherence Analysis Based on Deep Neural Network
Baiyun Cui, Yingming Li, Yaqing Zhang +1
In this paper, we propose a novel deep coherence model (DCM) using a convolutional neural network architecture to capture the text coherence. The text coherence problem is investig…
Transductive Zero-Shot Learning with a Self-training dictionary approach
Yunlong Yu, Zhong Ji, Xi Li +4
As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training dat…
Structural Correspondence Learning for Cross-lingual Sentiment Classification with One-to-many Mappings
Nana Li, Shuangfei Zhai, Zhongfei Zhang +1
Structural correspondence learning (SCL) is an effective method for cross-lingual sentiment classification. This approach uses unlabeled documents along with a word translation ora…
Generative Adversarial Networks as Variational Training of Energy Based Models
Shuangfei Zhai, Yu Cheng, Rogerio Feris +1
In this paper, we study deep generative models for effective unsupervised learning. We propose VGAN, which works by minimizing a variational lower bound of the negative log likelih…
A Survey of Multi-View Representation Learning
Yingming Li, Ming Yang, Zhongfei Zhang
Recently, multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas. This paper introduces two categories for multi-view r…