Haiyang Zheng
郑海阳

Haiyang Zheng

University of Trento

Multimedia and Human Understanding Group (MHUG)

📝 Publications

CVPR 2026 Paper
The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery
Haiyang Zheng, Nan Pu, Yaqi Cai, Teng Long, Wenjing Li, Nicu Sebe, Zhun Zhong.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
[Paper] [Code]
A plug-and-play gradient-level module that mitigates gradient entanglement and improves robust generalized category discovery.
ICMR 2023 Paper
Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning
Haiyang Zheng, Nan Pu, Wenjing Li, Teng Long, Nicu Sebe, Zhun Zhong.
AAAI Conference on Artificial Intelligence (AAAI), 2026.
[Paper] [Code]
Mitigating confidence skew and automatically estimating novel forgery types for robust open-world DeepFake attribution.
ICMR 2023 Paper
Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery
Xiao Liu, Nan Pu, Haiyang Zheng, Wenjing Li, Nicu Sebe, Zhun Zhong.
International Conference on Computer Vision (ICCV), 2025.
[Paper] [Code]
A diffusion-based framework that synthesizes and refines novel samples to enhance on-the-fly fine-grained category discovery.
Neurips 2024 Paper
Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery
Haiyang Zheng, Nan Pu, Wenjing Li, Nicu Sebe, and Zhun Zhong.
Neural Information Processing Systems (NeurIPS), 2024.
[Paper] [Code]
We propose a prototypical hash encoding method to discover fine-grained categories in real-time streams.
ECCV 2024 Paper
Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery
Haiyang Zheng, Nan Pu, Wenjing Li, Nicu Sebe, and Zhun Zhong.
European Conference on Computer Vision (ECCV), 2024.
[Paper] [Code]
Leveraging textual knowledge to guide visual discovery in generalized settings using a co-teaching framework.
ICMR 2024 Paper
Deep Image Clustering Based on Curriculum Learning and Density Information
Haiyang Zheng, Ruilin Zhang, Hongpeng Wang.
ACM International Conference on Multimedia Retrieval (ICMR), 2024.
[Paper]
Combining curriculum learning strategies with density peaks to improve deep clustering performance.
ICMR 2023 Paper
TDEC: Deep Embedded Image Clustering with Transformer and Distribution Information
Ruilin Zhang, Haiyang Zheng, Hongpeng Wang.
ACM International Conference on Multimedia Retrieval (ICMR), 2023.
[Paper]
A novel Transformer-based framework for deep embedded clustering that exploits distribution information.