Search Results for author:
Found 6 papers, 4 papers with code
Weight-Inherited Distillation for Task-Agnostic BERT Compression
Knowledge Distillation (KD) is a predominant approach for BERT compression.
Masked Autoencoders Are Stronger Knowledge Distillers
In MKD, random patches of the input image are masked, and the corresponding missing feature is recovered by forcing it to imitate the output of the teacher.
UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors
Bridging this semantic gap now requires case-by-case algorithm design which is time-consuming and heavily relies on experienced adjustment.
Rethinking Knowledge Distillation via Cross-Entropy
Furthermore, we smooth students' target output to treat it as the soft target for training without teachers and propose a teacher-free new KD loss (tf-NKD).
Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network
Image quality assessment (IQA) algorithm aims to quantify the human perception of image quality.
Ranked #1 on
Image Quality Assessment
on MSU FR VQA Database
MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
No-Reference Image Quality Assessment (NR-IQA) aims to assess the perceptual quality of images in accordance with human subjective perception.
Ranked #8 on
Video Quality Assessment
on MSU SR-QA Dataset
