Model compression for deep neural networks: A survey

Z Li, H Li, L Meng - Computers, 2023‏ - mdpi.com
Currently, with the rapid development of deep learning, deep neural networks (DNNs) have
been widely applied in various computer vision tasks. However, in the pursuit of …

Knowledge distillation and student-teacher learning for visual intelligence: A review and new outlooks

L Wang, KJ Yoon - IEEE transactions on pattern analysis and …, 2021‏ - ieeexplore.ieee.org
Deep neural models, in recent years, have been successful in almost every field, even
solving the most complex problem statements. However, these models are huge in size with …

Knowledge distillation: A survey

J Gou, B Yu, SJ Maybank, D Tao - International Journal of Computer Vision, 2021‏ - Springer
In recent years, deep neural networks have been successful in both industry and academia,
especially for computer vision tasks. The great success of deep learning is mainly due to its …

Knowledge distillation meets self-supervision

G Xu, Z Liu, X Li, CC Loy - European conference on computer vision, 2020‏ - Springer
Abstract Knowledge distillation, which involves extracting the “dark knowledge” from a
teacher network to guide the learning of a student network, has emerged as an important …

Exploring inter-channel correlation for diversity-preserved knowledge distillation

L Liu, Q Huang, S Lin, H **e, B Wang… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Abstract Knowledge Distillation has shown very promising ability in transferring learned
representation from the larger model (teacher) to the smaller one (student). Despite many …

A survey on green deep learning

J Xu, W Zhou, Z Fu, H Zhou, L Li - arxiv preprint arxiv:2111.05193, 2021‏ - arxiv.org
In recent years, larger and deeper models are springing up and continuously pushing state-
of-the-art (SOTA) results across various fields like natural language processing (NLP) and …

[PDF][PDF] Knowledge distillation via softmax regression representation learning

J Yang, B Martinez, A Bulat, G Tzimiropoulos - 2021‏ - qmro.qmul.ac.uk
This paper addresses the problem of model compression via knowledge distillation. We
advocate for a method that optimizes the output feature of the penultimate layer of the …

R-dfcil: Relation-guided representation learning for data-free class incremental learning

Q Gao, C Zhao, B Ghanem, J Zhang - European Conference on Computer …, 2022‏ - Springer
Abstract Class-Incremental Learning (CIL) struggles with catastrophic forgetting when
learning new knowledge, and Data-Free CIL (DFCIL) is even more challenging without …

Unpaired multi-modal segmentation via knowledge distillation

Q Dou, Q Liu, PA Heng… - IEEE transactions on …, 2020‏ - ieeexplore.ieee.org
Multi-modal learning is typically performed with network architectures containing modality-
specific layers and shared layers, utilizing co-registered images of different modalities. We …

More grounded image captioning by distilling image-text matching model

Y Zhou, M Wang, D Liu, Z Hu… - Proceedings of the …, 2020‏ - openaccess.thecvf.com
Visual attention not only improves the performance of image captioners, but also serves as a
visual interpretation to qualitatively measure the caption rationality and model transparency …