Sign In
insight - Image processing and analysis
Automating Threshold Selection for Relevant Image Retrieval in Automated Driving Systems Perception Testing
An automated method for determining a threshold value to efficiently retrieve relevant images from a dataset for perception testing of automated driving systems, balancing false positives and false negatives.
Towards Generalizable Fake Image Detection Across Diverse Generative Models
A feature space not explicitly trained for real-vs-fake classification can achieve significantly better generalization in detecting fake images from unseen generative models compared to deep learning based methods.
Unsupervised Learning for Text-based Image Tone Adjustment: CLIPtone, a Novel Framework
CLIPtone, an unsupervised learning-based approach, enables text-guided image tone adjustment by leveraging CLIP to assess perceptual alignment without requiring paired training data.
Products
© 2024 by Linnk AI