Jing Zhang

Jing Zhang is a Senior Lecturer HDR Co-Convener Intelligent Systems at the Australian National University (ANU), affiliated with the School of Computing. Her research interests include computer vision and machine learning, with a focus on generative AI, image, video, and audio generation and editing, explainable model adaptation and generalization, out-of-distribution detection and anomaly detection, and adversarial attacks and defenses. She is currently supervising four PhD students at ANU. Zhang earned her PhD from ANU in 2021, focusing on salient object detection, and previously served as a Research Fellow at ANU from 2021 to 2022. She has also contributed to academic conferences and journals as a reviewer and program committee member.

Jing Zhang is a lecturer at ANU College of Systems & Society, specializing in Robust and Reliable Representation Learning and Generative Models. Her research focuses on developing advanced methods for salient object detection, camouflaged object detection, and audio-visual segmentation. She explores techniques such as uncertainty-aware modeling, variational autoencoders, and energy-based latent spaces to enhance the reliability and robustness of generative models. Zhang's work also includes weakly-supervised learning, few-shot learning, and multimodal variational auto-encoders for improved image restoration and saliency prediction. Her research addresses challenges in handling noisy data, uncertainty estimation, and multimodal information integration.