Swin-L
PulseAugur coverage of Swin-L — every cluster mentioning Swin-L across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New lightweight AI extracts sidewalk paths for micromobility navigation
Researchers have developed a lightweight, machine learning-driven system for extracting sidewalk paths from monocular camera feeds, designed for embedded navigation in micromobility devices. The system, which underwent …
-
Transformer Model Excels at Detecting Tiny Pollinators in ECCV Challenge
Researchers have developed a novel Transformer-based model for detecting tiny pollinators in challenging field keyframes. The model, named Co-DINO with a Swin-L backbone, achieved the highest mean Average Precision (mAP…
-
Physics-inspired KSSE model achieves 88.93% ImageNet accuracy with reduced parameters
Researchers have developed a novel physics-inspired energy-based model called Kohn-Sham Spectral Embedding (KSSE) for image classification. KSSE replaces traditional dense Convolutional Neural Networks (CNNs) with a spa…
-
LLMs enhance food image segmentation with novel language injection modules
Researchers have developed two novel modules, LIM-F and LIM-Q, to enhance food image segmentation by integrating ingredient labels derived from large language models (LLMs). These modules can be added to existing image …