English
Related papers

Related papers: UNIFORM: Unifying Knowledge from Large-scale and D…

200 papers

Cross-modal knowledge distillation deals with transferring knowledge from a model trained with superior modalities (Teacher) to another model trained with weak modalities (Student). Existing approaches require paired training examples exist…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Long Zhao , Xi Peng , Yuxiao Chen , Mubbasir Kapadia , Dimitris N. Metaxas

Unified multimodal models aim to integrate understanding (text output) and generation (pixel output), but aligning these different modalities within a single architecture often demands complex training recipes and careful data balancing. We…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Xichen Pan , Satya Narayan Shukla , Aashu Singh , Zhuokai Zhao , Shlok Kumar Mishra , Jialiang Wang , Zhiyang Xu , Jiuhai Chen , Kunpeng Li , Felix Juefei-Xu , Ji Hou , Saining Xie

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

Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that…

Machine Learning · Computer Science 2025-02-11 Anna Vettoruzzo , Lorenzo Braccaioli , Joaquin Vanschoren , Marlena Nowaczyk

In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about…

This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks. Unlike most existing transfer learning methods that focus on fixing the discrepancy between supervised tasks, we…

Machine Learning · Computer Science 2020-09-25 Zhiyu Yao , Yunbo Wang , Mingsheng Long , Jianmin Wang

Transfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task. Here we explore the…

Software Engineering · Computer Science 2020-03-04 Natalie Best , Jordan Ott , Erik Linstead

When the transferable set is unknowable, transfering informative knowledge as much as possible\textemdash a principle we refer to as \emph{sufficiency}, becomes crucial for enhancing transfer learning effectiveness. However, existing…

Methodology · Statistics 2025-07-22 Xiyuan Zhang , Huihang Liu , Xinyu Zhang

Unified multimodal models are envisioned to bridge the gap between understanding and generation. Yet, to achieve competitive performance, state-of-the-art models adopt largely decoupled understanding and generation components. This design,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Zeyu Liu , Zanlin Ni , Yang Yue , Cheng Da , Huan Yang , Di Zhang , Kun Gai , Gao Huang

Pretrained deep models hold their learnt knowledge in the form of model parameters. These parameters act as "memory" for the trained models and help them generalize well on unseen data. However, in absence of training data, the utility of a…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Gaurav Kumar Nayak , Konda Reddy Mopuri , Saksham Jain , Anirban Chakraborty

Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concerns. Existing approaches typically modify model parameters, but such updates can be unstable,…

Machine Learning · Computer Science 2026-05-29 Antonio Almudévar , Alfonso Ortega

Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images like those in ImageNet and ignores the correlation among the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Zhaowen Li , Yousong Zhu , Fan Yang , Wei Li , Chaoyang Zhao , Yingying Chen , Zhiyang Chen , Jiahao Xie , Liwei Wu , Rui Zhao , Ming Tang , Jinqiao Wang

While deeper and wider neural networks are actively pushing the performance limits of various computer vision and machine learning tasks, they often require large sets of labeled data for effective training and suffer from extremely high…

Computer Vision and Pattern Recognition · Computer Science 2017-10-27 Zhi Zhang , Guanghan Ning , Zhihai He

Ensemble of machine learning models yields improved performance as well as robustness. However, their memory requirements and inference costs can be prohibitively high. Knowledge distillation is an approach that allows a single model to…

Computer Vision and Pattern Recognition · Computer Science 2022-10-06 Zhengcong Fei , Shuman Tian , Junshi Huang , Xiaoming Wei , Xiaolin Wei

To reduce the overwhelming size of Deep Neural Networks (DNN) teacher-student methodology tries to transfer knowledge from a complex teacher network to a simple student network. We instead propose a novel method called the teacher-class…

Machine Learning · Computer Science 2021-11-02 Shaiq Munir Malik , Muhammad Umair Haider , Mohbat Tharani , Musab Rasheed , Murtaza Taj

With the development of deep learning techniques, supervised learning has achieved performances surpassing those of humans. Researchers have designed numerous corresponding models for different data modalities, achieving excellent results…

Artificial Intelligence · Computer Science 2023-08-29 Qiang Li , Qiuyang Ma , Weizhi Nie , Anan Liu

Recent advances in large-scale pre-training provide large models with the potential to learn knowledge from the raw text. It is thus natural to ask whether it is possible to leverage these large models as knowledge bases for downstream…

Computation and Language · Computer Science 2022-11-09 Yanyang Li , Jianqiao Zhao , Michael R. Lyu , Liwei Wang

Knowledge distillation is an effective approach to learn compact models (students) with the supervision of large and strong models (teachers). As empirically there exists a strong correlation between the performance of teacher and student…

Machine Learning · Computer Science 2022-10-13 Chaofei Wang , Qisen Yang , Rui Huang , Shiji Song , Gao Huang

Many real-world tasks require models to compare images along multiple similarity conditions (e.g. similarity in color, category or shape). Existing methods often reason about these complex similarity relationships by learning…

Computer Vision and Pattern Recognition · Computer Science 2019-08-26 Reuben Tan , Mariya I. Vasileva , Kate Saenko , Bryan A. Plummer

This research investigates the enhancement of knowledge distillation (KD) processes in pre-trained models, an emerging field in knowledge transfer with significant implications for distributed training and federated learning environments.…

Machine Learning · Computer Science 2025-07-23 Norah Alballa , Ahmed M. Abdelmoniem , Marco Canini