Mixed-Precision Quantization (MQ) can achieve a competitive
accuracy-com...
Existing feature distillation methods commonly adopt the One-to-one
Repr...
Diffusion Probability Models (DPMs) have made impressive advancements in...
Knowledge distillation (KD) is an effective training strategy to improve...
Practical networks for edge devices adopt shallow depth and small
convol...
Neural architecture search (NAS) has made tremendous progress in the
aut...
It is of great significance to estimate the performance of a given model...
Neural architecture search methods seek optimal candidates with efficien...
Image-level weakly supervised semantic segmentation (WSSS) is a fundamen...
Recent advances in Automatic Speech Recognition (ASR) demonstrated how
e...
Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrate...
Nowadays, attention models are one of the popular candidates for speech
...