English
Related papers

Related papers: ERDE: Entropy-Regularized Distillation for Early-e…

200 papers

Knowledge distillation is effective to train small and generalisable network models for meeting the low-memory and fast running requirements. Existing offline distillation methods rely on a strong pre-trained teacher, which enables…

Computer Vision and Pattern Recognition · Computer Science 2018-09-11 Xu Lan , Xiatian Zhu , Shaogang Gong

We propose a simple yet effective method to compress an RNN-Transducer (RNN-T) through the well-known knowledge distillation paradigm. We show that the transducer's encoder outputs naturally have a high entropy and contain rich information…

Computation and Language · Computer Science 2021-06-16 Rupak Vignesh Swaminathan , Brian King , Grant P. Strimel , Jasha Droppo , Athanasios Mouchtaris

We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher…

Computer Vision and Pattern Recognition · Computer Science 2019-08-12 Byeongho Heo , Jeesoo Kim , Sangdoo Yun , Hyojin Park , Nojun Kwak , Jin Young Choi

Monocular depth estimation (MDE) methods are often either too computationally expensive or not accurate enough due to the trade-off between model complexity and inference performance. In this paper, we propose a lightweight network that can…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Junjie Hu , Chenyou Fan , Hualie Jiang , Xiyue Guo , Yuan Gao , Xiangyong Lu , Tin Lun Lam

Unstructured pruning remains a powerful strategy for compressing deep neural networks, yet it often demands iterative train-prune-retrain cycles, resulting in significant computational overhead. To address this challenge, we introduce a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Md. Samiul Alim , Sharjil Khan , Amrijit Biswas , Fuad Rahman , Shafin Rahman , Nabeel Mohammed

Knowledge distillation (KD) is one of the most potent ways for model compression. The key idea is to transfer the knowledge from a deep teacher model (T) to a shallower student (S). However, existing methods suffer from performance…

Machine Learning · Computer Science 2020-02-24 Mengya Gao , Yujun Shen , Quanquan Li , Chen Change Loy

Deep network compression has been achieved notable progress via knowledge distillation, where a teacher-student learning manner is adopted by using predetermined loss. Recently, more focuses have been transferred to employ the adversarial…

Machine Learning · Computer Science 2019-04-26 Shu Changyong , Li Peng , Xie Yuan , Qu Yanyun , Dai Longquan , Ma Lizhuang

DETR is a novel end-to-end transformer architecture object detector, which significantly outperforms classic detectors when scaling up. In this paper, we focus on the compression of DETR with knowledge distillation. While knowledge…

Computer Vision and Pattern Recognition · Computer Science 2025-06-26 Yu Wang , Xin Li , Shengzhao Weng , Gang Zhang , Haixiao Yue , Haocheng Feng , Junyu Han , Errui Ding

Structured prediction models aim at solving a type of problem where the output is a complex structure, rather than a single variable. Performing knowledge distillation for such models is not trivial due to their exponentially large output…

Machine Learning · Computer Science 2022-03-10 Wenye Lin , Yangming Li , Lemao Liu , Shuming Shi , Hai-tao Zheng

Data-free knowledge distillation is a challenging model lightweight task for scenarios in which the original dataset is not available. Previous methods require a lot of extra computational costs to update one or more generators and their…

Computer Vision and Pattern Recognition · Computer Science 2023-02-24 Yuzheng Wang , Zuhao Ge , Zhaoyu Chen , Xian Liu , Chuangjia Ma , Yunquan Sun , Lizhe Qi

Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Huan Wang , Suhas Lohit , Michael Jones , Yun Fu

This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…

Computation and Language · Computer Science 2024-12-30 Shuo Wang , Chihang Wang , Jia Gao , Zhen Qi , Hongye Zheng , Xiaoxuan Liao

Knowledge distillation (KD) is a well-known technique to effectively compress a large network (teacher) to a smaller network (student) with little sacrifice in performance. However, most KD methods require a large training set and internal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Tri-Nhan Vo , Dang Nguyen , Kien Do , Sunil Gupta

Modern search systems use several large ranker models with transformer architectures. These models require large computational resources and are not suitable for usage on devices with limited computational resources. Knowledge distillation…

High storage and computational costs obstruct deep neural networks to be deployed on resource-constrained devices. Knowledge distillation aims to train a compact student network by transferring knowledge from a larger pre-trained teacher…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Haoran Zhao , Xin Sun , Junyu Dong , Changrui Chen , Zihe Dong

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 scalability to encode large-scale data and to maneuver…

Machine Learning · Computer Science 2021-05-21 Jianping Gou , Baosheng Yu , Stephen John Maybank , Dacheng Tao

Transformer-based reinforcement learning has emerged as a strong candidate for sequential control in residential energy management. In particular, the Decision Transformer can learn effective battery dispatch policies from historical data,…

Machine Learning · Computer Science 2026-03-30 Pascal Henrich , Jonas Sievers , Maximilian Beichter , Thomas Blank , Ralf Mikut , Veit Hagenmeyer

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Xinhao Zhong , Shuoyang Sun , Xulin Gu , Zhaoyang Xu , Yaowei Wang , Min Zhang , Bin Chen

Knowledge distillation, aimed at transferring the knowledge from a heavy teacher network to a lightweight student network, has emerged as a promising technique for compressing neural networks. However, due to the capacity gap between the…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Xuewei Li , Songyuan Li , Bourahla Omar , Fei Wu , Xi Li

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

Computer Vision and Pattern Recognition · Computer Science 2020-06-24 Ruoyu Sun , Fuhui Tang , Xiaopeng Zhang , Hongkai Xiong , Qi Tian