English
Related papers

Related papers: DDFAD: Dataset Distillation Framework for Audio Da…

200 papers

Dataset distillation (DD) aims to construct compact synthetic datasets that allow models to achieve comparable performance to full-data training while substantially reducing storage and computation. Despite rapid empirical progress, its…

Machine Learning · Computer Science 2025-12-11 Zhengquan Luo , Zhiqiang Xu

We propose an algorithm that compresses the critical information of a large dataset into compact addressable memories. These memories can then be recalled to quickly re-train a neural network and recover the performance (instead of storing…

Machine Learning · Computer Science 2022-11-22 Zhiwei Deng , Olga Russakovsky

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

Computation and Language · Computer Science 2021-03-18 Kevin J Liang , Weituo Hao , Dinghan Shen , Yufan Zhou , Weizhu Chen , Changyou Chen , Lawrence Carin

As a promising approach in model compression, knowledge distillation improves the performance of a compact model by transferring the knowledge from a cumbersome one. The kind of knowledge used to guide the training of the student is…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Tao Liu , Xi Yang , Chenshu Chen

Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher…

Machine Learning · Computer Science 2020-08-04 Yushuo Guan , Pengyu Zhao , Bingxuan Wang , Yuanxing Zhang , Cong Yao , Kaigui Bian , Jian Tang

FM Synthesis is a well-known algorithm used to generate complex timbre from a compact set of design primitives. Typically featuring a MIDI interface, it is usually impractical to control it from an audio source. On the other hand,…

Sound · Computer Science 2022-08-15 Franco Caspe , Andrew McPherson , Mark Sandler

Data-Free Knowledge Distillation (DFKD) plays a vital role in compressing the model when original training data is unavailable. Previous works for DFKD in NLP mainly focus on distilling encoder-only structures like BERT on classification…

Computation and Language · Computer Science 2023-11-06 Zheyuan Bai , Xinduo Liu , Hailin Hu , Tianyu Guo , Qinghua Zhang , Yunhe Wang

This paper explores the use of knowledge distillation to improve a Multi-Task Deep Neural Network (MT-DNN) (Liu et al., 2019) for learning text representations across multiple natural language understanding tasks. Although ensemble learning…

Computation and Language · Computer Science 2019-04-23 Xiaodong Liu , Pengcheng He , Weizhu Chen , Jianfeng Gao

Deep Neural Networks (DNNs) have significantly advanced the field of computer vision. To improve DNN training process, knowledge distillation methods demonstrate their effectiveness in accelerating network training by introducing a fixed…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Daqian Shi , Xiaolei Diao , Xu Chen , Cédric M. John

Dataset Distillation (DD), a newly emerging field, aims at generating much smaller but efficient synthetic training datasets from large ones. Existing DD methods based on gradient matching achieve leading performance; however, they are…

Machine Learning · Computer Science 2023-04-18 Lei Zhang , Jie Zhang , Bowen Lei , Subhabrata Mukherjee , Xiang Pan , Bo Zhao , Caiwen Ding , Yao Li , Dongkuan Xu

Medical image enhancement is clinically valuable, but existing methods require large-scale datasets to learn complex pixel-level mappings. However, the substantial training and storage costs associated with these datasets hinder their…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Fengzhi Xu , Ziyuan Yang , Mengyu Sun , Joey Tianyi Zhou , Yi Zhang

In recent times, large datasets hinder efficient model training while also containing redundant concepts. Dataset distillation aims to synthesize compact datasets that preserve the knowledge of large-scale training sets while drastically…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Ayush Roy , Wei-Yang Alex Lee , Rudrasis Chakraborty , Vishnu Suresh Lokhande

Dataset distillation has become a popular method for compressing large datasets into smaller, more efficient representations while preserving critical information for model training. Data features are broadly categorized into two types:…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Minh-Tuan Tran , Trung Le , Xuan-May Le , Thanh-Toan Do , Dinh Phung

Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recently proposed neural network-based unsupervised learning…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Takahiko Furuya , Ryutarou Ohbuchi

Techniques such as ensembling and distillation promise model quality improvements when paired with almost any base model. However, due to increased test-time cost (for ensembles) and increased complexity of the training pipeline (for…

Machine Learning · Computer Science 2020-08-24 Rohan Anil , Gabriel Pereyra , Alexandre Passos , Robert Ormandi , George E. Dahl , Geoffrey E. Hinton

To meet the demand for designing efficient neural networks with appropriate trade-offs between model performance (e.g., classification accuracy) and computational complexity, the differentiable neural architecture distillation (DNAD)…

Machine Learning · Computer Science 2025-04-30 Xuan Rao , Bo Zhao , Derong Liu

Recent multi-modal models have shown remarkable versatility in real-world applications. However, their rapid development encounters two critical data challenges. First, the training process requires large-scale datasets, leading to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Zhuohang Dang , Minnan Luo , Chengyou Jia , Hangwei Qian , Xiaojun Chang , Ivor W. Tsang

Dataset Distillation (DD) is designed to generate condensed representations of extensive image datasets, enhancing training efficiency. Despite recent advances, there remains considerable potential for improvement, particularly in…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Bowen Yuan , Zijian Wang , Mahsa Baktashmotlagh , Yadan Luo , Zi Huang

Acoustic event detection for content analysis in most cases relies on lots of labeled data. However, manually annotating data is a time-consuming task, which thus makes few annotated resources available so far. Unlike audio event detection,…

Computer Vision and Pattern Recognition · Computer Science 2016-08-16 Yong Xu , Qiang Huang , Wenwu Wang , Philip J. B. Jackson , Mark D. Plumbley

Dataset distillation (DD) compresses large datasets into smaller ones while preserving the performance of models trained on them. Although DD is often assumed to enhance data privacy by aggregating over individual examples, recent studies…

Cryptography and Security · Computer Science 2025-11-14 Shuo Shi , Jinghuai Zhang , Shijie Jiang , Chunyi Zhou , Yuyuan Li , Mengying Zhu , Yangyang Wu , Tianyu Du