English
Related papers

Related papers: Class-aware Information for Logit-based Knowledge …

200 papers

Gait recognition is an attractive biometric modality for long-range and contact-free identification, but high-performing gait models often rely on deep and computationally expensive architectures that are difficult to deploy in practice.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Yuqi Li , Qian Zhou , Huiran Duan , Jingjie Wang , Shunli Zhang , Chuanguang Yang , Guoying Zhao , Yingli Tian

State-of-the-art logit distillation methods exhibit versatility, simplicity, and efficiency. Despite the advances, existing studies have yet to delve thoroughly into fine-grained relationships within logit knowledge. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Liuchi Xu , Kang Liu , Jinshuai Liu , Lu Wang , Lisheng Xu , Jun Cheng

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

Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue;…

Computation and Language · Computer Science 2023-11-08 Manas Mohanty , Tanya Roosta , Peyman Passban

Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Li Yuan , Francis E. H. Tay , Guilin Li , Tao Wang , Jiashi Feng

Knowledge Distillation has shown very promising abil-ity in transferring learned representation from the largermodel (teacher) to the smaller one (student).Despitemany efforts, prior methods ignore the important role ofretaining…

Computer Vision and Pattern Recognition · Computer Science 2022-02-09 Li Liu , Qingle Huang , Sihao Lin , Hongwei Xie , Bing Wang , Xiaojun Chang , Xiaodan Liang

Knowledge distillation transfers knowledge from the teacher network to the student one, with the goal of greatly improving the performance of the student network. Previous methods mostly focus on proposing feature transformation and loss…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Pengguang Chen , Shu Liu , Hengshuang Zhao , Jiaya Jia

Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…

Computation and Language · Computer Science 2024-06-18 Qihuang Zhong , Liang Ding , Li Shen , Juhua Liu , Bo Du , Dacheng Tao

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

Since pioneering work of Hinton et al., knowledge distillation based on Kullback-Leibler Divergence (KL-Div) has been predominant, and recently its variants have achieved compelling performance. However, KL-Div only compares probabilities…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Jiaming Lv , Haoyuan Yang , Peihua Li

Despite its breakthrough in classification problems, Knowledge distillation (KD) to recommendation models and ranking problems has not been studied well in the previous literature. This dissertation is devoted to developing knowledge…

Information Retrieval · Computer Science 2024-07-22 SeongKu Kang

Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research…

Information Retrieval · Computer Science 2024-08-28 Nikhil Khani , Shuo Yang , Aniruddh Nath , Yang Liu , Pendo Abbo , Li Wei , Shawn Andrews , Maciej Kula , Jarrod Kahn , Zhe Zhao , Lichan Hong , Ed Chi

In recent years, deep learning has spread rapidly, and deeper, larger models have been proposed. However, the calculation cost becomes enormous as the size of the models becomes larger. Various techniques for compressing the size of the…

Machine Learning · Computer Science 2020-04-20 Hideki Oki , Motoshi Abe , Junichi Miyao , Takio Kurita

Knowledge distillation (KD), a technique widely employed in computer vision, has emerged as a de facto standard for improving the performance of small neural networks. However, prevailing KD-based approaches in video tasks primarily focus…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Guiqin Wang , Peng Zhao , Yanjiang Shi , Cong Zhao , Shusen Yang

Knowledge distillation transfers knowledge from a high capacity teacher to a compact student using a mixture of hard and soft losses. On imbalanced data, a fixed weighting between hard and soft losses becomes brittle the learning process.…

Machine Learning · Computer Science 2026-05-20 Anh B. H. Nguyen , Ba Tho Phan , Viet Cuong Ta

To apply the latest computer vision techniques that require a large computational cost in real industrial applications, knowledge distillation methods (KDs) are essential. Existing logit-based KDs apply the constant temperature scaling to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Seonghak Kim , Gyeongdo Ham , Suin Lee , Donggon Jang , Daeshik Kim

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

Computation and Language · Computer Science 2025-11-18 Haiduo Huang , Jiangcheng Song , Yadong Zhang , Pengju Ren

We propose Cross-Attention-based Non-local Knowledge Distillation (CanKD), a novel feature-based knowledge distillation framework that leverages cross-attention mechanisms to enhance the knowledge transfer process. Unlike traditional…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Shizhe Sun , Wataru Ohyama

In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Xu Zheng , Yunhao Luo , Pengyuan Zhou , Lin Wang

This paper addresses the problem of model compression via knowledge distillation. To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from…

Computer Vision and Pattern Recognition · Computer Science 2020-03-11 Jing Yang , Brais Martinez , Adrian Bulat , Georgios Tzimiropoulos