4 papers
Is Task-Specific Training Necessary for Anomaly Detection?
Xingwu Zhang, Guanxuan Li, Paul Henderson +2
Current state-of-the-art multi-class unsupervised anomaly detection (MUAD) methods rely on training encoder--decoder models to reconstruct anomaly-free features. However, we argue…
ADaFuSE: Adaptive Diffusion-generated Image and Text Fusion for Interactive Text-to-Image Retrieval
Zhuocheng Zhang, Xingwu Zhang, Kangheng Liang +3
Recent advances in interactive text-to-image retrieval (I-TIR) use diffusion models to bridge the modality gap between the textual information need and the images to be searched, r…
Eliminating Hallucination in Diffusion-Augmented Interactive Text-to-Image Retrieval
Zhuocheng Zhang, Kangheng Liang, Guanxuan Li +3
Diffusion-Augmented Interactive Text-to-Image Retrieval (DAI-TIR) is a promising paradigm that improves retrieval performance by generating query images via diffusion models and us…
RoboEye: Enhancing 2D Robotic Object Identification with Selective 3D Geometric Keypoint Matching
Xingwu Zhang, Guanxuan Li, Zhuocheng Zhang +1
The rapidly growing number of product categories in large-scale e-commerce makes accurate object identification for automated packing in warehouses substantially more difficult. As…