STKD: Distilling Knowledge From Synchronous Teaching for Efficient Model Compression.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3164264
Abstract: Knowledge distillation (KD) transfers discriminative knowledge from a large and complex model (known as teacher) to a smaller and faster one (known as student). Existing advanced KD methods, limited to fixed feature extraction paradigms that… read more here.
Keywords: comprehensive knowledge; synchronous teaching; knowledge; model ... See more keywords