ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Sheng-Jun Huang

Sheng-Jun Huang

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

20

papers

252

total citations

papers (20)

Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training

NEURIPS 2021arXiv

Active Learning for Open-Set Annotation

Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery

Can Adversarial Training Be Manipulated By Non-Robust Features?

NEURIPS 2022arXiv

Unlocking the Power of Open Set: A New Perspective for Open-Set Noisy Label Learning

Multi-Label Knowledge Distillation

Dirichlet-Based Prediction Calibration for Learning with Noisy Labels

Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training

Bidirectional Uncertainty-Based Active Learning for Open-Set Annotation

MLC-NC: Long-Tailed Multi-Label Image Classification Through the Lens of Neural Collapse

Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach

Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL

One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

Improving Generalization of Deep Neural Networks by Optimum Shifting

Label-Aware Global Consistency for Multi-Label Learning with Single Positive Labels

Active Learning for Multiple Target Models

Multi-Label Learning with Pairwise Relevance Ordering

Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning

StructSR: Refuse Spurious Details in Real-World Image Super-Resolution

Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning