4 citations · 6 across the 8 of their papers we have counts for
8 papers
On the Adversarial Robustness of Multimodal LLM Judges
Zihan Wang, Guansong Pang, Zelin Liu +3
Multimodal Large Language Models (MLLMs) are increasingly used as automated judges, e.g., for image quality and safety assessment. However, their adversarial robustness remains lar…
Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation
Wenjun Miao, Guansong Pang, Jin Zheng +1
One key challenge in Out-of-Distribution (OOD) detection is the absence of ground-truth OOD samples during training. One principled approach to address this issue is to use samples…
OpenCIL: Benchmarking Out-of-Distribution Detection in Class-Incremental Learning
Wenjun Miao, Guansong Pang, Trong-Tung Nguyen +3
Class incremental learning (CIL) aims to learn a model that can not only incrementally accommodate new classes, but also maintain the learned knowledge of old classes. Out-of-distr…
Learning Transferable Negative Prompts for Out-of-Distribution Detection
Tianqi Li, Guansong Pang, Xiao Bai +2
Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead…
Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning
Wenjun Miao, Guansong Pang, Tianqi Li +2
Existing out-of-distribution (OOD) methods have shown great success on balanced datasets but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples are…
Towards Fully Decoupled End-to-End Person Search
Pengcheng Zhang, Xiao Bai, Jin Zheng +1
End-to-end person search aims to jointly detect and re-identify a target person in raw scene images with a unified model. The detection task unifies all persons while the re-id tas…
Unsupervised Recognition of Unknown Objects for Open-World Object Detection
Ruohuan Fang, Guansong Pang, Lei Zhou +2
Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known a…
Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worlds
Tianqi Li, Guansong Pang, Xiao Bai +3
Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-worl…