English
Related papers

Related papers: Evolving Knowledge Distillation for Lightweight Ne…

200 papers

Knowledge Distillation (KD) is one proposed solution to large model sizes and slow inference speed in semantic segmentation. In our research we identify 25 proposed distillation loss terms from 14 publications in the last 4 years.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Onno Niemann , Christopher Vox , Thorben Werner

Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge devices. Although their combination is quite promising to…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Jangho Kim , Yash Bhalgat , Jinwon Lee , Chirag Patel , Nojun Kwak

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Computation and Language · Computer Science 2024-07-04 Jongwoo Ko , Sungnyun Kim , Tianyi Chen , Se-Young Yun

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

Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved in two aspects: the…

Computation and Language · Computer Science 2024-07-04 Ying Zhang , Ziheng Yang , Shufan Ji

In knowledge distillation, the knowledge from the teacher model is often too complex for the student model to thoroughly process. However, good teachers in real life always simplify complex material before teaching it to students. Inspired…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Mengyang Yuan , Bo Lang , Fengnan Quan

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

Although Deep neural networks (DNNs) have shown a strong capacity to solve large-scale problems in many areas, such DNNs are hard to be deployed in real-world systems due to their voluminous parameters. To tackle this issue, Teacher-Student…

Machine Learning · Computer Science 2023-08-09 Chengming Hu , Xuan Li , Dan Liu , Haolun Wu , Xi Chen , Ju Wang , Xue Liu

Knowledge distillation establishes a learning paradigm that leverages both data supervision and teacher guidance. However, determining the optimal balance between learning from data and learning from the teacher is challenging, as some…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Jingchen Sun , Shaobo Han , Deep Patel , Wataru Kohno , Can Jin , Changyou Chen

Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile devices also arises, such as the AI assistant software. Some…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Qianhan Feng , Wenshuo Li , Tong Lin , Xinghao Chen

Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the…

Computation and Language · Computer Science 2024-10-02 Songming Zhang , Xue Zhang , Zengkui Sun , Yufeng Chen , Jinan Xu

Knowledge distillation is used, in generative language modeling, to train a smaller student model using the help of a larger teacher model, resulting in improved capabilities for the student model. In this paper, we formulate a more general…

Computation and Language · Computer Science 2025-02-26 Guanlin Liu , Anand Ramachandran , Tanmay Gangwani , Yan Fu , Abhinav Sethy

Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer. However, almost all existing KD algorithms are data-driven, i.e., relying on a large…

Machine Learning · Computer Science 2020-03-03 Gongfan Fang , Jie Song , Chengchao Shen , Xinchao Wang , Da Chen , Mingli Song

Knowledge distillation (KD) is a promising solution to compress large language models (LLMs) by transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output…

Computation and Language · Computer Science 2025-04-16 Xue Zhang , Songming Zhang , Yunlong Liang , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

With the emergence of Mixture-of-Experts (MoE), the efficient scaling of model size has accelerated the development of large language models in recent years. However, their high memory requirements prevent their use in resource-constrained…

Computation and Language · Computer Science 2025-02-19 Gyeongman Kim , Gyouk Chu , Eunho Yang

In the past few years, transformer-based pre-trained language models have achieved astounding success in both industry and academia. However, the large model size and high run-time latency are serious impediments to applying them in…

Computation and Language · Computer Science 2022-07-13 Chengqiang Lu , Jianwei Zhang , Yunfei Chu , Zhengyu Chen , Jingren Zhou , Fei Wu , Haiqing Chen , Hongxia Yang

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…

Artificial Intelligence · Computer Science 2023-01-31 Chaochen Gao , Xing Wu , Peng Wang , Jue Wang , Liangjun Zang , Zhongyuan Wang , Songlin Hu

Knowledge distillation (KD) is essential for training non-autoregressive translation (NAT) models by reducing the complexity of the raw data with an autoregressive teacher model. In this study, we empirically show that as a side effect of…

Computation and Language · Computer Science 2021-01-28 Liang Ding , Longyue Wang , Xuebo Liu , Derek F. Wong , Dacheng Tao , Zhaopeng Tu

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

Computation and Language · Computer Science 2019-08-27 Siqi Sun , Yu Cheng , Zhe Gan , Jingjing Liu

Existing knowledge distillation (KD) methods have demonstrated their ability in achieving student network performance on par with their teachers. However, the knowledge gap between the teacher and student remains significant and may hinder…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Shuoxi Zhang , Zijian Song , Kun He