Tag: focal loss

A new multi-scale deep learning framework called Rain-PostEFNet substantially improves numerical weather prediction rainfall forecasts, with the largest gains in ...

Researchers have introduced Light-wDEF, a resource-efficient and fully reproducible framework that enabled a fair comparison of ten visual deepfake detectors ...

A new framework pairs momentum contrastive learning with the GATv2 graph attention network to detect rare, legally entangled financial credit ...

Researchers at Hohai University have developed ShuffleNet-MSAA, a lightweight AI system that uses adaptive attention and sonar imaging to detect ...

Researchers have developed a real-time computer vision system that reads students' facial expressions during online lessons and converts four learning-centered ...

KAIST researchers combined physics-based preprocessing with a FiLM-conditioned convolutional neural network to classify weld defects in phased-array ultrasonic testing, reaching ...

Researchers in Beijing have built a 0.27-megabyte transformer model that detects multi-stage APT attacks in industrial IoT telemetry with high ...

A new deep learning model called CWT-AuxNet converts wavelet-based time-frequency representations of uterine electrical recordings into individualized preterm birth risk ...

Researchers have developed a focused positive-unlabeled learning method that uses focal loss to achieve state-of-the-art performance on severely imbalanced datasets ...

A new baseline study shows that deep learning can learn meaningful microstructural information from severely imbalanced ultra-high carbon steel images, ...