4 papers
ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation
Xiwei Xuan, Ziquan Deng, Kwan-Liu Ma
Training-free open-vocabulary semantic segmentation (OVS) aims to segment images given a set of arbitrary textual categories without costly model fine-tuning. Existing solutions of…
A Reliable Framework for Human-in-the-Loop Anomaly Detection in Time Series
Ziquan Deng, Xiwei Xuan, Kwan-Liu Ma +1
Time series anomaly detection is a critical machine learning task for numerous applications, such as finance, healthcare, and industrial systems. However, even high-performing mode…
SLIM: Spuriousness Mitigation with Minimal Human Annotations
Xiwei Xuan, Ziquan Deng, Hsuan-Tien Lin +1
Recent studies highlight that deep learning models often learn spurious features mistakenly linked to labels, compromising their reliability in real-world scenarios where such corr…
SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspective
Xiwei Xuan, Ziquan Deng, Hsuan-Tien Lin +2
Researchers have proposed various methods for visually interpreting the Convolutional Neural Network (CNN) via saliency maps, which include Class-Activation-Map (CAM) based approac…