Tag: knowledge distillation

Researchers in South Korea have developed a progressive distillation framework called ASBQ that trains one-bit binary neural networks to match ...

Researchers have developed FedML-DKD, a federated learning framework that uses Earth Mover's Distance to adaptively balance knowledge distillation and meta-learning, ...

A hybrid compression framework combining knowledge distillation, quantization-aware training, and dynamic inference achieves 92.3 percent semantic accuracy at 1.5 watts ...

A new self-supervised framework called AnomalyMHKD combines self-distillation, cross-architecture distillation and dynamic teacher freezing to detect industrial anomalies with up ...

Researchers have unveiled a weakly supervised AI framework that segments crops, weeds and soil from image-level labels alone, achieving 76.04 ...

Researchers compressed transformer-based tabular neural networks by up to 38-fold using knowledge distillation and deployed them on an NVIDIA Jetson ...

Researchers at Shenzhen Technology University report a LiDAR segmentation framework that reaches 74.4 percent mean IoU on SemanticKITTI and 83.5 ...

Researchers have developed a spectrum-guided, teacher–student AI framework that adapts its time windows to the rhythms of unlabeled system logs ...

Researchers have released EmbedKD, an open-source toolkit that brings verified diagnostics, retrieval protocols and reproducible deployment checks to the compression ...

Researchers have developed SRRI, a source-free domain adaptation method that uses CLIP as an external verifier to de-bias pseudo-source domains ...