Search Results - "Geng, Chuanxing"

Collective Decision for Open Set Recognition by Geng, Chuanxing, Chen, Songcan

“…In open set recognition (OSR), almost all existing methods are designed specially for recognizing individual instances, even these instances are collectively…”
Get full text

Multiplane Convex Proximal Support Vector Machine by Geng, Chuanxing, Chen, Songcan

“…As an effective method for XOR problems, generalized eigenvalue proximal support vector machine (GEPSVM) recently has gained widespread attention accompanied…”
Get full text

Recent Advances in Open Set Recognition: A Survey by Geng, Chuanxing, Huang, Sheng-Jun, Chen, Songcan

“…In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all…”
Get full text

Metric Learning-Guided Least Squares Classifier Learning by Geng, Chuanxing, Chen, Songcan

“…For a multicategory classification problem, discriminative least squares regression (DLSR) explicitly introduces an <inline-formula> <tex-math…”
Get full text

Guided CNN for generalized zero-shot and open-set recognition using visual and semantic prototypes by Geng, Chuanxing, Tao, Lue, Chen, Songcan

“…•Decomposing G-ZSL task into an OSR task and a ZSL task while jointly.•training the models of these two tasks effectively addresses the CO problem which is…”
Get full text

Universum-inspired Supervised Contrastive Learning by Han, Aiyang, Geng, Chuanxing, Chen, Songcan

“…As an effective data augmentation method, Mixup synthesizes an extra amount of samples through linear interpolations. Despite its theoretical dependency on…”
Get full text

A comprehensive perspective of contrastive self-supervised learning by CHEN, Songcan, GENG, Chuanxing

Get full text

Collective Decision for Open Set Recognition (Extended Abstract) by Geng, Chuanxing, Chen, Songcan

“…In open set recognition (OSR), almost all existing methods are designed specially for recognizing individual instances, even these instances are collectively…”
Get full text

Dynamic Learnable Logit Adjustment for Long-Tailed Visual Recognition by Zhang, Enhao, Geng, Chuanxing, Li, Chaohua, Chen, Songcan

“…Logit adjustment is an effective long-tailed visual recognition strategy to encourage a significant margin between rare and dominant labels. Existing methods…”
Get full text

Convergence analysis of an accelerated expectation-maximization algorithm for ill-posed integral equations by Geng, Chuanxing, Wang, Jinping

“…The maximum‐likelihood expectation‐maximization (EM) algorithm has attracted considerable interest in single‐photon emission computed tomography, because it…”
Get full text

Universum-inspired Supervised Contrastive Learning by Han, Aiyang, Geng, Chuanxing, Chen, Songcan

“…As an effective data augmentation method, Mixup synthesizes an extra amount of samples through linear interpolations. Despite its theoretical dependency on…”
Get full text

Collective decision for open set recognition by Geng, Chuanxing, Chen, Songcan

“…In open set recognition (OSR), almost all existing methods are designed specially for recognizing individual instances, even these instances are collectively…”
Get full text

All-around Neural Collapse for Imbalanced Classification by Zhang, Enhao, Li, Chaohua, Geng, Chuanxing, Chen, Songcan

“…Neural Collapse (NC) presents an elegant geometric structure that enables individual activations (features), class means and classifier (weights) vectors to…”
Get full text

Dynamic Against Dynamic: An Open-set Self-learning Framework by Yang, Haifeng, Geng, Chuanxing, Yuen, Pong C, Chen, Songcan

“…In open-set recognition, existing methods generally learn statically fixed decision boundaries using known classes to reject unknown classes. Though they have…”
Get full text

Class-Aware Universum Inspired Re-Balance Learning for Long-Tailed Recognition by Zhang, Enhao, Geng, Chuanxing, Chen, Songcan

“…Data augmentation for minority classes is an effective strategy for long-tailed recognition, thus developing a large number of methods. Although these methods…”
Get full text

All Beings Are Equal in Open Set Recognition by Li, Chaohua, Zhang, Enhao, Geng, Chuanxing, Chen, SongCan

“…In open-set recognition (OSR), a promising strategy is exploiting pseudo-unknown data outside given $K$ known classes as an additional $K$+$1$-th class to…”
Get full text

View-labels Are Indispensable: A Multifacet Complementarity Study of Multi-view Clustering by Geng, Chuanxing, Han, Aiyang, Chen, Songcan

“…Consistency and complementarity are two key ingredients for boosting multi-view clustering (MVC). Recently with the introduction of popular contrastive…”
Get full text

Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning by Wang, Xinrui, Geng, Chuanxing, Wan, Wenhai, Li, Shao-yuan, Chen, Songcan

“…Online continual learning requires the models to learn from constant, endless streams of data. While significant efforts have been made in this field, most…”
Get full text

Leave Zero Out: Towards a No-Cross-Validation Approach for Model Selection by Li, Weikai, Geng, Chuanxing, Chen, Songcan

“…As the main workhorse for model selection, Cross Validation (CV) has achieved an empirical success due to its simplicity and intuitiveness. However, despite…”
Get full text

A Multi-view Perspective of Self-supervised Learning by Geng, Chuanxing, Tan, Zhenghao, Chen, Songcan

“…As a newly emerging unsupervised learning paradigm, self-supervised learning (SSL) recently gained widespread attention, which usually introduces a pretext…”
Get full text