NCNing Chen
Ning Chen
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Ning Chen has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Shen-Huan Lyu
College of Computer Science and Software Engineering, Hohai University, Nanjing, China
3 shared publications - Tian-Shuang Wu2 shared publications
- Yanyan Wang
College of Computer Science and Software Engineering, Hohai University, Nanjing, China
2 shared publications - Baoliu Ye
Nanjing University
1 shared publication - Bin Tang
Hohai University
1 shared publication - Can Jiao
Key Laboratory of Water Big Data Technology of Ministry of Water Resources, College of Computer Science and Software Engineering, Hohai University, Nanjing 210098, China
1 shared publication
Latest Publications
- Open Access
- 10 September 2026
- Published by MDPI AG in Electronics
- Vol. 15 (18) , 4108
Confidence-Aware Relation Contrastive Learning for Partial Multi-Label Learning
Partial multi-label learning (PML) learns from over-complete candidate labels: All true labels are included in the candidate set, but irrelevant labels may also be annotated. Existing PML methods mainly reduce this ambiguity during classifier training by estimating label reliability, recovering latent label distributions, or modeling label correlations. This paper studies a complementary question: how can PML supervision be used for contrastive representation pretraining? The main difficulty is relation construction. Raw candidate label overlap is not a reliable contrastive signal, because two images can share only false candidate labels. We therefore formulate PML pretraining as a relation disambiguation problem and propose a confidence-aware relation contrastive learning framework. The method estimates candidate label confidence, uses it to construct semantic relation distributions over current and queued samples, and aligns the embedding distribution with these confidence-weighted relations. The same candidate label confidence semantics are used during downstream fine-tuning, keeping non-candidate labels as reliable negatives while softly disambiguating the candidate set. Across VOC2007, NUS-WIDE, and COCO2014, the method improves subset accuracy and F1-oriented measures under moderate and severe partial-label noise. For example, on VOC2007 at , it improves subset accuracy from 0.3322 to 0.5269 and micro-F1 from 0.6710 to 0.7617 over PML-CD. However, the CUB200 results further identify a limitation: fine-grained attribute prediction is less consistently served by the present global representation pretraining design.- 10 September 2026
- Published by MDPI AG in Electronics
- Vol. 15 (18) , 4108
Open AccessConfidence-Aware Relation Contrastive Learning for Partial Multi-Label Learning
Partial multi-label learning (PML) learns from over-complete candidate labels: All true labels are included in the candidate set, but irrelevant labels may also be annotated. Existing PML methods mainly reduce this ambiguity during classifier training by estimating label reliability, recovering latent label distributions, or modeling label correlations. This paper studies a complementary question: how can PML supervision be used for contrastive representation pretraining? The main difficulty is relation construction. Raw candidate label overlap is not a reliable contrastive signal, because two images can share only false candidate labels. We therefore formulate PML pretraining as a relation disambiguation problem and propose a confidence-aware relation contrastive learning framework. The method estimates candidate label confidence, uses it to construct semantic relation distributions over current and queued samples, and aligns the embedding distribution with these confidence-weighted relations. The same candidate label confidence semantics are used during downstream fine-tuning, keeping non-candidate labels as reliable negatives while softly disambiguating the candidate set. Across VOC2007, NUS-WIDE, and COCO2014, the method improves subset accuracy and F1-oriented measures under moderate and severe partial-label noise. For example, on VOC2007 at , it improves subset accuracy from 0.3322 to 0.5269 and micro-F1 from 0.6710 to 0.7617 over PML-CD. However, the CUB200 results further identify a limitation: fine-grained attribute prediction is less consistently served by the present global representation pretraining design. - 13 January 2026
- Published by Elsevier in Pattern Recognition Letters
- Vol. 201, 117-124
Compressing model with few class-imbalance samples: An out-of-distribution expedition
- 13 January 2026
- Published by Elsevier in Pattern Recognition Letters
- Vol. 201, 117-124
Compressing model with few class-imbalance samples: An out-of-distribution expedition
- 27 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 174
Improving multi-label contrastive learning by leveraging label distribution
- 27 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 174
Improving multi-label contrastive learning by leveraging label distribution