1k citations · 1.6k across the 54 of their papers we have counts for
54 papers
Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery
Yuyan Zhou, Dong Liang, Songcan Chen +3
When taking images against strong light sources, the resulting images often contain heterogeneous flare artifacts. These artifacts can importantly affect image visual quality and d…
No Regularization is Needed: An Efficient and Effective Model for Incomplete Label Distribution Learning
Xiang Li, Songcan Chen
Label Distribution Learning (LDL) assigns soft labels, a.k.a. degrees, to a sample. In reality, it is always laborious to obtain complete degrees, giving birth to the Incomplete LD…
ALL-E: Aesthetics-guided Low-light Image Enhancement
Ling Li, Dong Liang, Yuanhang Gao +2
Evaluating the performance of low-light image enhancement (LLE) is highly subjective, thus making integrating human preferences into image enhancement a necessity. Existing methods…
Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learning
Wenhai Wan, Xinrui Wang, Ming-Kun Xie +3
Learning from noisy data has attracted much attention, where most methods focus on closed-set label noise. However, a more common scenario in the real world is the presence of both…
Near-Optimal Decentralized Momentum Method for Nonconvex-PL Minimax Problems
Feihu Huang, Songcan Chen
Minimax optimization plays an important role in many machine learning tasks such as generative adversarial networks (GANs) and adversarial training. Although recently a wide variet…
Pushing One Pair of Labels Apart Each Time in Multi-Label Learning: From Single Positive to Full Labels
Xiang Li, Xinrui Wang, Songcan Chen
In Multi-Label Learning (MLL), it is extremely challenging to accurately annotate every appearing object due to expensive costs and limited knowledge. When facing such a challenge,…
PointSmile: Point Self-supervised Learning via Curriculum Mutual Information
Xin Li, Mingqiang Wei, Songcan Chen
Self-supervised learning is attracting wide attention in point cloud processing. However, it is still not well-solved to gain discriminative and transferable features of point clou…
Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing Labels
Zhongchen Ma, Lisha Li, Qirong Mao +1
Contrastive learning (CL) has shown impressive advances in image representation learning in whichever supervised multi-class classification or unsupervised learning. However, these…
Class-Aware Universum Inspired Re-Balance Learning for Long-Tailed Recognition
Enhao Zhang, Chuanxing Geng, Songcan Chen
Data augmentation for minority classes is an effective strategy for long-tailed recognition, thus developing a large number of methods. Although these methods all ensure the balanc…
Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox
Yunyun Wang, Yao Liu, Songcan Chen
Universal domain adaptation (UniDA) is a general unsupervised domain adaptation setting, which addresses both domain and label shifts in adaptation. Its main challenge lies in how…
Dual-Correction Adaptation Network for Noisy Knowledge Transfer
Yunyun Wang, Weiwen Zheng, Songcan Chen
Previous unsupervised domain adaptation (UDA) methods aim to promote target learning via a single-directional knowledge transfer from label-rich source domain to unlabeled target d…
Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks
Jiaqiang Zhang, Senzhang Wang, Songcan Chen
Detecting abnormal nodes from attributed networks is of great importance in many real applications, such as financial fraud detection and cyber security. This task is challenging d…
Explicit View-labels Matter: A Multifacet Complementarity Study of Multi-view Clustering
Chuanxing Geng, Aiyang Han, Songcan Chen
Consistency and complementarity are two key ingredients for boosting multi-view clustering (MVC). Recently with the introduction of popular contrastive learning, the consistency le…
Jacobian Norm for Unsupervised Source-Free Domain Adaptation
Weikai Li, Meng Cao, Songcan Chen
Unsupervised Source (data) Free domain adaptation (USFDA) aims to transfer knowledge from a well-trained source model to a related but unlabeled target domain. In such a scenario,…
A Novel Splitting Criterion Inspired by Geometric Mean Metric Learning for Decision Tree
Dan Li, Songcan Chen
Decision tree (DT) attracts persistent research attention due to its impressive empirical performance and interpretability in numerous applications. However, the growth of traditio…
Universum-inspired Supervised Contrastive Learning
Aiyang Han, Chuanxing Geng, Songcan Chen
As an effective data augmentation method, Mixup synthesizes an extra amount of samples through linear interpolations. Despite its theoretical dependency on data properties, Mixup r…
Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Jiayu Yao, Qingyuan Wu, Quan Feng +1
Self-supervised learning (SSL), as a newly emerging unsupervised representation learning paradigm, generally follows a two-stage learning pipeline: 1) learning invariant and discri…
A Similarity-based Framework for Classification Task
Zhongchen Ma, Songcan Chen
Similarity-based method gives rise to a new class of methods for multi-label learning and also achieves promising performance. In this paper, we generalize this method, resulting i…
Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task
Quan Feng, Songcan Chen
Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where la…
Can Adversarial Training Be Manipulated By Non-Robust Features?
Lue Tao, Lei Feng, Hongxin Wei +3
Adversarial training, originally designed to resist test-time adversarial examples, has shown to be promising in mitigating training-time availability attacks. This defense ability…
Rectified Euler k-means and Beyond
Yunxia Lin, Songcan chen
Euler k-means (EulerK) first maps data onto the unit hyper-sphere surface of equi-dimensional space via a complex mapping which induces the robust Euler kernel and next employs the…
Partial Domain Adaptation without Domain Alignment
Weikai Li, Songcan Chen
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a well-labeled source domain to a different but related unlabeled target domain with identical label space. Cur…
Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries
Kun-Peng Ning, Lue Tao, Songcan Chen +1
In addition to high accuracy, robustness is becoming increasingly important for machine learning models in various applications. Recently, much research has been devoted to improvi…
Leave Zero Out: Towards a No-Cross-Validation Approach for Model Selection
Weikai Li, Chuanxing Geng, Songcan Chen
As the main workhorse for model selection, Cross Validation (CV) has achieved an empirical success due to its simplicity and intuitiveness. However, despite its ubiquitous role, CV…