Search papers, labs, and topics across Lattice.
6
0
5
Domain shifts can degrade vehicle attribute classification performance more than the choice of model architecture, revealing critical vulnerabilities in real-world applications.
Recognition performance in face recognition systems can vary dramatically based on image quality, revealing hidden biases that challenge existing benchmarks.
Achieving a 4.36脳 speed-up in face synthesis without sacrificing image quality could revolutionize the generation of large-scale synthetic face datasets.
Achieving a remarkable F1-Score of 93.45, VeriCam redefines how we tackle zero-shot classification of unknown classes in biased real-world datasets.
FASR++ transforms low-quality surveillance images into high-resolution facial representations, achieving state-of-the-art recognition accuracy without compromising identity integrity.
Achieving a macro accuracy of 79.7% in vehicle color recognition highlights the potential of synthetic data augmentation to address severe class imbalances in surveillance contexts.
