Possible advisorsa guess from early papers, not confirmed

• Wee Siong Ng

  Possible advisor · last author on 6 of their early first-author papers, 2020–2023

  Suggested from co-authorship

Is this you? Claim this profile to confirm or dismiss it.

• LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks

  Adam Goodge, Bryan Hooi, See Kiong Ng, Wee Siong Ng

  Proceedings of the AAAI Conference on Artificial Intelligence · 2022

  This paper proposes LUNAR, a novel, graph neural network-based anomaly detection method that performs significantly better than existing local outlier methods, as well as state-of-the-art deep baselines, and is much more robust to different settings of the local neighbourhood size.

  171
• Robustness of Autoencoders for Anomaly Detection Under Adversarial Impact

  Adam Goodge, Bryan Hooi, See Kiong Ng, Wee Siong Ng

  International Joint Conference on Artificial Intelligence · 2020

  The Approximate Projection Autoencoder (APAE), which incorporates two defenses against such attacks against an adversarial attack into a general autoencoders, and involves a novel technique to improve robustness under adversarial impact by optimising latent representations for better reconstruction outputs.

  75
• COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection

  Jingyi Liao, Xun Xu, Manh Cuong Nguyen, Adam Goodge, Chuan-Sheng Foo

  IEEE Transactions on Image Processing · 2024

  This paper proposes a novel methodology to address the challenge of FSAD which incorporates a model pre-trained on a large source dataset to initialize model weights and adopts contrastive training to fine-tune on the few-shot target domain data.

  38
• Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model

  Yushu Li, Yongyi Su, Adam Goodge, Kui Jia, Xun Xu

  arXiv · 2024

  This work dynamically constructs a graph over text prompts, few-shot examples, and test samples, using label propagation for inference without task-specific tuning, and introduces a context-aware feature re-weighting mechanism to improve task adaptation accuracy.

  11
• Spatio-Temporal Foundation Models: Vision, Challenges, and Opportunities

  Adam Goodge, Wee Siong Ng, Bryan Hooi, See Kiong Ng

  arXiv · 2025

  A vision for the future of STFMs is articulated, outlining their essential characteristics and the generalization capabilities necessary for broad applicability, and identifying gaps relative to these ideal traits.

  8
• CADET: Calibrated Anomaly Detection for Mitigating Hardness Bias

  Ailin Deng, Adam Goodge, Lang Yi Ang, Bryan Hooi

  International Joint Conference on Artificial Intelligence · 2022

  This paper proposes an efficient and plug-and-play error calibration method which mitigates this hardness bias in the anomaly scoring without the need to retrain the model.

  6
• SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation

  Adam Goodge, Xu, Xun, Bryan Hooi, Wee Siong Ng, Jingyi Liao, Yongyi Su, Xulei Yang

  arXiv · 2025

  A novel methodology called SODA is proposed which improves the detection of OOD point clouds through a neighborhood-based score propagation scheme that is inference-based, requires no additional model training, and achieves state-of-the-art performance over existing approaches across datasets and problem settings.

  1
• Exploiting Vision Language Model for Training-Free 3D Point Cloud Understanding via Improved Graph Score Propagation

  Tiankai Chen, Yushu Li, Adam Goodge, Fei Teng, Xulei Yang, Zhen Liang, Tianrui Li, Xun Xu

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026

  GSP++ is presented, a graph-based inference framework that exploits the manifold structure of test-time point clouds to refine VLM scores without additional training, and introduces a self-training strategy that selects high-confidence positive and negative samples and assigns them calibrated pseudo scores to further stabilize propagation.

  –
• Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagation

  Tiankai Chen, Yushu Li, Adam Goodge, Fei Teng, Xulei Yang, Tianrui Li, Xun Xu

  IEEE/CVF International Conference on Computer Vision (ICCV) · 2025

  A novel Graph Score Propagation (GSP) method that incorporates prompt clustering and self-training negative prompting to improve OOD scoring with VLM is proposed and demonstrated that GSP consistently outperforms state-of-the-art methods across synthetic and realworld datasets for 3D point cloud OOD detection.

  –
• ARES: Locally Adaptive Reconstruction-Based Anomaly Scoring

  Adam Goodge, Bryan Hooi, See Kiong Ng, Wee Siong Ng

  Lecture notes in computer science · 2023

  –