Tag: knowledge distillation

Researchers in Tokyo have developed a transfer learning framework that encodes the topology of a source domain's feature space into ...

A new study systematically benchmarks five CNN compression techniques across GPUs, CPUs, and noisy data, finding that the best choice ...

A new cross-modality knowledge distillation framework uses CT-derived feature supervision to boost chest X-ray classification of lung diseases by up ...

Researchers in Vietnam have developed WGPose-LL, a deep learning method that uses paired well-lit images to guide human pose estimation ...

Researchers in Chongqing have built a lightweight camera-only 3D detection framework that adapts its processing to scene complexity, fuses information ...

Researchers have developed SURGE, a graph unlearning framework that treats data deletion requests as structural perturbations and repairs graph neural ...

Researchers in China have developed a deep neural network fingerprinting method that explicitly separates stolen model copies from independently trained ...

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 ...