English
Related papers

Related papers: KIND: Knowledge Integration and Diversion for Trai…

200 papers

In the era of deep learning, the increasing number of pre-trained models available online presents a wealth of knowledge. These models, developed with diverse architectures and trained on varied datasets for different tasks, provide unique…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Yimu Wang , Weiming Zhuang , Chen Chen , Jiabo Huang , Jingtao Li , Lingjuan Lyu

Pre-training is crucial for learning deep neural networks. Most of existing pre-training methods train simple models (e.g., restricted Boltzmann machines) and then stack them layer by layer to form the deep structure. This layer-wise…

Machine Learning · Computer Science 2015-06-09 Zhiyuan Tang , Dong Wang , Yiqiao Pan , Zhiyong Zhang

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

Recent advances in knowledge distillation have emphasized the importance of decoupling different knowledge components. While existing methods utilize momentum mechanisms to separate task-oriented and distillation gradients, they overlook…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Haiduo Huang , Jiangcheng Song , Yadong Zhang , Pengju Ren

Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is…

Machine Learning · Computer Science 2021-03-02 Jiaxi Tang , Rakesh Shivanna , Zhe Zhao , Dong Lin , Anima Singh , Ed H. Chi , Sagar Jain

Increased training parameters have enabled large pre-trained models to excel in various downstream tasks. Nevertheless, the extensive computational requirements associated with these models hinder their widespread adoption within the…

Artificial Intelligence · Computer Science 2024-11-12 Yu-Liang Zhan , Zhong-Yi Lu , Hao Sun , Ze-Feng Gao

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

Curriculum learning is a class of training strategies that organizes the data being exposed to a model by difficulty, gradually from simpler to more complex examples. This research explores a reverse curriculum generation approach that…

Machine Learning · Computer Science 2026-02-25 Wanru Zhao , Lucas Caccia , Zhengyan Shi , Minseon Kim , Weijia Xu , Alessandro Sordoni

This study addresses the Domain-Class Incremental Learning problem, a realistic but challenging continual learning scenario where both the domain distribution and target classes vary across tasks. To handle these diverse tasks, pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Longxiang Tang , Zhuotao Tian , Kai Li , Chunming He , Hantao Zhou , Hengshuang Zhao , Xiu Li , Jiaya Jia

In Natural Language Processing (NLP), Transformers have already revolutionized the field by utilizing an attention-based encoder-decoder model. Recently, some pioneering works have employed Transformer-like architectures in Computer Vision…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Gousia Habib , Tausifa Jan Saleem , Brejesh Lall

Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Roy Miles , Ismail Elezi , Jiankang Deng

Training and deploying multiple vision transformer (ViT) models for different resource constraints is costly and inefficient. To address this, we propose transforming a pre-trained ViT into a stratified knowledge-density super-network,…

Machine Learning · Computer Science 2025-11-18 Longhua Li , Lei Qi , Xin Geng

In the context of high usability in single-class anomaly detection models, recent academic research has become concerned about the more complex multi-class anomaly detection. Although several papers have designed unified models for this…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Xi Jiang , Ying Chen , Qiang Nie , Jianlin Liu , Yong Liu , Chengjie Wang , Feng Zheng

The increased availability of the multi-view data (data on the same samples from multiple sources) has led to strong interest in models based on low-rank matrix factorizations. These models represent each data view via shared and individual…

Machine Learning · Statistics 2021-04-01 Irina Gaynanova , Gen Li

This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Mingsheng Li , Lin Zhang , Mingzhen Zhu , Zilong Huang , Gang Yu , Jiayuan Fan , Tao Chen

We propose a compression based continual task learning method that can dynamically grow a neural network. Inspired from the recent model compression techniques, we employ compression-aware training and perform low-rank weight approximations…

Computer Vision and Pattern Recognition · Computer Science 2020-09-16 Varigonda Pavan Teja , Priyadarshini Panda

Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications.…

Computation and Language · Computer Science 2022-11-03 Haojie Pan , Chengyu Wang , Minghui Qiu , Yichang Zhang , Yaliang Li , Jun Huang

Data-free knowledge distillation is able to utilize the knowledge learned by a large teacher network to augment the training of a smaller student network without accessing the original training data, avoiding privacy, security, and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 He Liu , Yikai Wang , Huaping Liu , Fuchun Sun , Anbang Yao

For many real-world time series tasks, the computational complexity of prevalent deep leaning models often hinders the deployment on resource-limited environments (e.g., smartphones). Moreover, due to the inevitable domain shift between…

Machine Learning · Computer Science 2023-07-10 Qing Xu , Min Wu , Xiaoli Li , Kezhi Mao , Zhenghua Chen

Continual learning (CL) aims to train models that can learn a sequence of tasks without forgetting previously acquired knowledge. A core challenge in CL is balancing stability -- preserving performance on old tasks -- and plasticity --…

Machine Learning · Computer Science 2025-05-14 Zhenrong Liu , Janne M. J. Huttunen , Mikko Honkala