α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Sheng-Jun Huang
Sheng-Jun Huang
20
papers
252
total citations
papers (20)
Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
NEURIPS 2021
arXiv
83
citations
Active Learning for Open-Set Annotation
CVPR 2022
arXiv
45
citations
Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery
ICCV 2023
arXiv
33
citations
Can Adversarial Training Be Manipulated By Non-Robust Features?
NEURIPS 2022
arXiv
17
citations
Unlocking the Power of Open Set: A New Perspective for Open-Set Noisy Label Learning
AAAI 2024
arXiv
15
citations
Multi-Label Knowledge Distillation
ICCV 2023
arXiv
14
citations
Dirichlet-Based Prediction Calibration for Learning with Noisy Labels
AAAI 2024
arXiv
12
citations
Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
ICML 2024
arXiv
9
citations
Bidirectional Uncertainty-Based Active Learning for Open-Set Annotation
ECCV 2024
arXiv
6
citations
MLC-NC: Long-Tailed Multi-Label Image Classification Through the Lens of Neural Collapse
AAAI 2025
6
citations
Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach
CVPR 2025
arXiv
4
citations
Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
ICML 2025
arXiv
4
citations
One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
ICLR 2024
arXiv
4
citations
Improving Generalization of Deep Neural Networks by Optimum Shifting
AAAI 2025
arXiv
0
citations
Label-Aware Global Consistency for Multi-Label Learning with Single Positive Labels
NEURIPS 2022
0
citations
Active Learning for Multiple Target Models
NEURIPS 2022
0
citations
Multi-Label Learning with Pairwise Relevance Ordering
NEURIPS 2021
0
citations
Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning
NEURIPS 2023
0
citations
StructSR: Refuse Spurious Details in Real-World Image Super-Resolution
AAAI 2025
arXiv
0
citations
Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning
ECCV 2024
arXiv
0
citations