16 citations · 33 across the 21 of their papers we have counts for
10 papers · 1 filter
GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models
Hongkuan Zhou, Tristan Rehm, Nadeem Nazer +3
Industrial inspection requires more than binary anomaly detection: a practical system should determine whether an anomaly exists, localize the defective region, identify the defect…
Defect-aware Hybrid Prompt Optimization via Progressive Tuning for Zero-Shot Multi-type Anomaly Detection and Segmentation
Nadeem Nazer, Hongkuan Zhou, Lavdim Halilaj +2
Recent vision-language models (VLMs) like CLIP have shown impressive anomaly detection performance under significant distribution shift by utilizing high-level semantic information…
Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive Learning
Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka +5
Open-domain visual entity recognition aims to identify and link entities depicted in images to a vast and evolving set of real-world concepts, such as those found in Wikidata. Unli…
DiffSemanticFusion: Semantic Raster BEV Fusion for Autonomous Driving via Online HD Map Diffusion
Zhigang Sun, Yiru Wang, Anqing Jiang +13
Autonomous driving requires accurate scene understanding, including road geometry, traffic agents, and their semantic relationships. In online HD map generation scenarios, raster-b…
MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning
Ylli Sadikaj, Hongkuan Zhou, Lavdim Halilaj +3
Precise optical inspection in industrial applications is crucial for minimizing scrap rates and reducing the associated costs. Besides merely detecting if a product is anomalous or…
Robust Visual Representation Learning with Multi-modal Prior Knowledge for Image Classification Under Distribution Shift
Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka +4
Despite the remarkable success of deep neural networks (DNNs) in computer vision, they fail to remain high-performing when facing distribution shifts between training and testing d…
SemanticFormer: Holistic and Semantic Traffic Scene Representation for Trajectory Prediction using Knowledge Graphs
Zhigang Sun, Zixu Wang, Lavdim Halilaj +1
Trajectory prediction in autonomous driving relies on accurate representation of all relevant contexts of the driving scene, including traffic participants, road topology, traffic…
nuScenes Knowledge Graph -- A comprehensive semantic representation of traffic scenes for trajectory prediction
Leon Mlodzian, Zhigang Sun, Hendrik Berkemeyer +5
Trajectory prediction in traffic scenes involves accurately forecasting the behaviour of surrounding vehicles. To achieve this objective it is crucial to consider contextual inform…
A Survey on Visual Transfer Learning using Knowledge Graphs
Sebastian Monka, Lavdim Halilaj, Achim Rettinger
Recent approaches of computer vision utilize deep learning methods as they perform quite well if training and testing domains follow the same underlying data distribution. However,…
Learning Visual Models using a Knowledge Graph as a Trainer
Sebastian Monka, Lavdim Halilaj, Stefan Schmid +1
Traditional computer vision approaches, based on neural networks (NN), are typically trained on a large amount of image data. By minimizing the cross-entropy loss between a predict…