6 citations · 9 across the 7 of their papers we have counts for
7 papers
Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples
Philipp J. Rösch, Norbert Oswald, Michaela Geierhos +1
Current multimodal models leveraging contrastive learning often face limitations in developing fine-grained conceptual understanding. This is due to random negative samples during…
dacl1k: Real-World Bridge Damage Dataset Putting Open-Source Data to the Test
Johannes Flotzinger, Philipp J. Rösch, Norbert Oswald +1
Recognising reinforced concrete defects (RCDs) is a crucial element for determining the structural integrity, traffic safety and durability of bridges. However, most of the existin…
dacl10k: Benchmark for Semantic Bridge Damage Segmentation
Johannes Flotzinger, Philipp J. Rösch, Thomas Braml
Reliably identifying reinforced concrete defects (RCDs)plays a crucial role in assessing the structural integrity, traffic safety, and long-term durability of concrete bridges, whi…
Probing the Role of Positional Information in Vision-Language Models
Philipp J. Rösch, Jindřich Libovický
In most Vision-Language models (VL), the understanding of the image structure is enabled by injecting the position information (PI) about objects in the image. In our case study of…
Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model
Fabian Deuser, Konrad Habel, Philipp J. Rösch +1
Current architectures for multi-modality tasks such as visual question answering suffer from their high complexity. As a result, these architectures are difficult to train and requ…
Building Inspection Toolkit: Unified Evaluation and Strong Baselines for Damage Recognition
Johannes Flotzinger, Philipp J. Rösch, Norbert Oswald +1
In recent years, several companies and researchers have started to tackle the problem of damage recognition within the scope of automated inspection of built structures. While comp…