English
Related papers

Related papers: CTPD: Cross Tokenizer Preference Distillation

200 papers

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-20 Ji Won Yoon , Hyeonseung Lee , Hyung Yong Kim , Won Ik Cho , Nam Soo Kim

Knowledge Distillation (KD) for object detection aims to train a compact detector by transferring knowledge from a teacher model. Since the teacher model perceives data in a way different from humans, existing KD methods only distill…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Jiawei Liang , Siyuan Liang , Aishan Liu , Ke Ma , Jingzhi Li , Xiaochun Cao

The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that knowledge distillation (KD), especially the mean-teacher…

Computer Vision and Pattern Recognition · Computer Science 2021-07-08 Xiaohan Xing , Yuenan Hou , Hang Li , Yixuan Yuan , Hongsheng Li , Max Q. -H. Meng

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Cheng Cui , Ruoyu Guo , Yuning Du , Dongliang He , Fu Li , Zewu Wu , Qiwen Liu , Shilei Wen , Jizhou Huang , Xiaoguang Hu , Dianhai Yu , Errui Ding , Yanjun Ma

Knowledge distillation (KD), best known as an effective method for model compression, aims at transferring the knowledge of a bigger network (teacher) to a much smaller network (student). Conventional KD methods usually employ the teacher…

Machine Learning · Computer Science 2023-08-14 Ji Won Yoon , Hyung Yong Kim , Hyeonseung Lee , Sunghwan Ahn , Nam Soo Kim

Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on privileged information unavailable to the student. Such…

Previous logits-based Knowledge Distillation (KD) have utilized predictions about multiple categories within each sample (i.e., class predictions) and have employed Kullback-Leibler (KL) divergence to reduce the discrepancy between the…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Gyeongdo Ham , Seonghak Kim , Suin Lee , Jae-Hyeok Lee , Daeshik Kim

Cross-modality distillation arises as an important topic for data modalities containing limited knowledge such as depth maps and high-quality sketches. Such techniques are of great importance, especially for memory and privacy-restricted…

Machine Learning · Computer Science 2024-05-29 Hangyu Lin , Chen Liu , Chengming Xu , Zhengqi Gao , Yanwei Fu , Yuan Yao

Knowledge distillation offers a promising path to transfer reasoning capabilities from large teacher models to efficient student models; however, existing token-level on-policy distillation methods require token-level alignment between the…

Computation and Language · Computer Science 2026-01-30 Jing Xiong , Hui Shen , Shansan Gong , Yuxin Cheng , Jianghan Shen , Chaofan Tao , Haochen Tan , Haoli Bai , Lifeng Shang , Ngai Wong

Typical technique in knowledge distillation (KD) is regularizing the learning of a limited capacity model (student) by pushing its responses to match a powerful model's (teacher). Albeit useful especially in the penultimate layer and…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Ada Gorgun , Yeti Z. Gurbuz , A. Aydin Alatan

Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distilled to train a…

Computer Vision and Pattern Recognition · Computer Science 2019-08-05 Frederick Tung , Greg Mori

Knowledge distillation is a popular paradigm for learning portable neural networks by transferring the knowledge from a large model into a smaller one. Most existing approaches enhance the student model by utilizing the similarity…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Haoran Zhao , Kun Gong , Xin Sun , Junyu Dong , Hui Yu

In the field of large language models (LLMs), Knowledge Distillation (KD) is a critical technique for transferring capabilities from teacher models to student models. However, existing KD methods face limitations and challenges in…

Computation and Language · Computer Science 2025-04-08 Yixing Li , Yuxian Gu , Li Dong , Dequan Wang , Yu Cheng , Furu Wei

Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models that are pre-trained…

Computation and Language · Computer Science 2023-03-08 Jinjie Ni , Yukun Ma , Wen Wang , Qian Chen , Dianwen Ng , Han Lei , Trung Hieu Nguyen , Chong Zhang , Bin Ma , Erik Cambria

Training a small student network with the guidance of a larger teacher network is an effective way to promote the performance of the student. Despite the different types, the guided knowledge used to distill is always kept unchanged for…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Jiangfan Han , Mengya Gao , Yujie Wang , Quanquan Li , Hongsheng Li , Xiaogang Wang

Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of Automatic Speech Recognition (ASR), distillation from…

Machine Learning · Computer Science 2021-07-06 Yan Gao , Titouan Parcollet , Nicholas Lane

On-policy knowledge distillation (OPD) trains a student on its own rollouts under token-level supervision from a teacher. Not all token positions matter equally, but existing views of token importance are incomplete. We ask a direct…

Machine Learning · Computer Science 2026-05-22 Yuanda Xu , Hejian Sang , Zhengze Zhou , Ran He , Zhipeng Wang , Alborz Geramifard

In Knowledge Distillation, the teacher is generally much larger than the student, making the solution of the teacher likely to be difficult for the student to learn. To ease the mimicking difficulty, we introduce a triplet knowledge…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Xijun Wang , Dongyang Liu , Meina Kan , Chunrui Han , Zhongqin Wu , Shiguang Shan

In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Ngoc Tuyen Do , Tri Nhu Do

Knowledge distillation aims to transfer representation ability from a teacher model to a student model. Previous approaches focus on either individual representation distillation or inter-sample similarity preservation. While we argue that…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Jinguo Zhu , Shixiang Tang , Dapeng Chen , Shijie Yu , Yakun Liu , Aijun Yang , Mingzhe Rong , Xiaohua Wang