791 citations · 1.5k across the 57 of their papers we have counts for
59 papers
Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts
Zhili Liu, Kai Chen, Jianhua Han +4
Masked Autoencoder~(MAE) is a prevailing self-supervised learning method that achieves promising results in model pre-training. However, when the various downstream tasks have data…
Domain-Guided Conditional Diffusion Model for Unsupervised Domain Adaptation
Yulong Zhang, Shuhao Chen, Weisen Jiang +3
Limited transferability hinders the performance of deep learning models when applied to new application scenarios. Recently, Unsupervised Domain Adaptation (UDA) has achieved signi…
GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training
Xinchi Deng, Han Shi, Runhui Huang +7
Cross-modal pre-training has shown impressive performance on a wide range of downstream tasks, benefiting from massive image-text pairs collected from the Internet. In practice, on…
Illumination Controllable Dehazing Network based on Unsupervised Retinex Embedding
Jie Gui, Xiaofeng Cong, Lei He +2
On the one hand, the dehazing task is an illposedness problem, which means that no unique solution exists. On the other hand, the dehazing task should take into account the subject…
Nonparametric Iterative Machine Teaching
Chen Zhang, Xiaofeng Cao, Weiyang Liu +2
In this paper, we consider the problem of Iterative Machine Teaching (IMT), where the teacher provides examples to the learner iteratively such that the learner can achieve fast co…
Effective Structured Prompting by Meta-Learning and Representative Verbalizer
Weisen Jiang, Yu Zhang, James T. Kwok
Prompt tuning for pre-trained masked language models (MLM) has shown promising performance in natural language processing tasks with few labeled examples. It tunes a prompt for the…
A Survey on Time-Series Pre-Trained Models
Qianli Ma, Zhen Liu, Zhenjing Zheng +4
Time-Series Mining (TSM) is an important research area since it shows great potential in practical applications. Deep learning models that rely on massive labeled data have been ut…
No Place to Hide: Dual Deep Interaction Channel Network for Fake News Detection based on Data Augmentation
Biwei Cao, Lulu Hua, Jiuxin Cao +3
Online Social Network (OSN) has become a hotbed of fake news due to the low cost of information dissemination. Although the existing methods have made many attempts in news content…
Fooling the Image Dehazing Models by First Order Gradient
Jie Gui, Xiaofeng Cong, Chengwei Peng +2
The research on the single image dehazing task has been widely explored. However, as far as we know, no comprehensive study has been conducted on the robustness of the well-trained…
Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning
Jidong Ge, Yuxiang Liu, Jie Gui +5
Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations…
AlignVE: Visual Entailment Recognition Based on Alignment Relations
Biwei Cao, Jiuxin Cao, Jie Gui +5
Visual entailment (VE) is to recognize whether the semantics of a hypothesis text can be inferred from the given premise image, which is one special task among recent emerged visio…
Searching a High-Performance Feature Extractor for Text Recognition Network
Hui Zhang, Quanming Yao, James T. Kwok +1
Feature extractor plays a critical role in text recognition (TR), but customizing its architecture is relatively less explored due to expensive manual tweaking. In this work, inspi…
A Survey of Learning on Small Data: Generalization, Optimization, and Challenge
Xiaofeng Cao, Weixin Bu, Shengjun Huang +4
Learning on big data brings success for artificial intelligence (AI), but the annotation and training costs are expensive. In future, learning on small data that approximates the g…
Low-rank Tensor Learning with Nonconvex Overlapped Nuclear Norm Regularization
Quanming Yao, Yaqing Wang, Bo Han +1
Nonconvex regularization has been popularly used in low-rank matrix learning. However, extending it for low-rank tensor learning is still computationally expensive. To address this…
Revisiting Over-smoothing in BERT from the Perspective of Graph
Han Shi, Jiahui Gao, Hang Xu +5
Recently over-smoothing phenomenon of Transformer-based models is observed in both vision and language fields. However, no existing work has delved deeper to further investigate th…
Dropout's Dream Land: Generalization from Learned Simulators to Reality
Zac Wellmer, James T. Kwok
A World Model is a generative model used to simulate an environment. World Models have proven capable of learning spatial and temporal representations of Reinforcement Learning env…
Bilinear Scoring Function Search for Knowledge Graph Learning
Yongqi Zhang, Quanming Yao, James Tin-Yau Kwok
Learning embeddings for entities and relations in knowledge graph (KG) have benefited many downstream tasks. In recent years, scoring functions, the crux of KG learning, have been…
Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution
Huapeng Wu, Jie Gui, Jun Zhang +2
Recently, deep convolutional neural network methods have achieved an excellent performance in image superresolution (SR), but they can not be easily applied to embedded devices due…
Feedback Pyramid Attention Networks for Single Image Super-Resolution
Huapeng Wu, Jie Gui, Jun Zhang +2
Recently, convolutional neural network (CNN) based image super-resolution (SR) methods have achieved significant performance improvement. However, most CNN-based methods mainly foc…
TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
Haoang Chi, Feng Liu, Wenjing Yang +5
In few-shot domain adaptation (FDA), classifiers for the target domain are trained with accessible labeled data in the source domain (SD) and few labeled data in the target domain…
SparseBERT: Rethinking the Importance Analysis in Self-attention
Han Shi, Jiahui Gao, Xiaozhe Ren +4
Transformer-based models are popularly used in natural language processing (NLP). Its core component, self-attention, has aroused widespread interest. To understand the self-attent…
Topology-aware Tensor Decomposition for Meta-graph Learning
Hansi Yang, Peiyu Zhang, Quanming Yao
Heterogeneous graphs generally refers to graphs with different types of nodes and edges. A common approach for extracting useful information from heterogeneous graphs is to use met…
A Survey of Label-noise Representation Learning: Past, Present and Future
Bo Han, Quanming Yao, Tongliang Liu +4
Classical machine learning implicitly assumes that labels of the training data are sampled from a clean distribution, which can be too restrictive for real-world scenarios. However…
A Scalable, Adaptive and Sound Nonconvex Regularizer for Low-rank Matrix Completion
Yaqing Wang, Quanming Yao, James T. Kwok
Matrix learning is at the core of many machine learning problems. A number of real-world applications such as collaborative filtering and text mining can be formulated as a low-ran…