3 papers
cs.CV2025
KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration
Chengyuan Li, Suyang Zhou, Jieping Kong +2
Zero-shot anomaly detection (ZSAD) identifies anomalies without needing training samples from the target dataset, essential for scenarios with privacy concerns or limited data. Vis…
cs.CV2024
Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP
Yayuan Li, Jintao Guo, Lei Qi +2
Contrastive Language-Image Pretraining (CLIP) has been widely used in vision tasks. Notably, CLIP has demonstrated promising performance in few-shot learning (FSL). However, existi…
cs.LG2024
Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
Qi Zhang, Yifei Wang, Jingyi Cui +4
Deep learning models often suffer from a lack of interpretability due to polysemanticity, where individual neurons are activated by multiple unrelated semantics, resulting in uncle…