English
Related papers

Related papers: Reminding the Incremental Language Model via Data-…

200 papers

Knowledge distillation (KD) requires sufficient data to transfer knowledge from large-scale teacher models to small-scale student models. Therefore, data augmentation has been widely used to mitigate the shortage of data under specific…

Computation and Language · Computer Science 2023-05-23 Ziqi Wang , Chi Han , Wenxuan Bao , Heng Ji

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

Although substantial efforts have been made to mitigate catastrophic forgetting in continual learning, the intrinsic mechanisms are not well understood. In this work, we demonstrate the existence of "pseudo forgetting": the performance…

Machine Learning · Computer Science 2025-06-10 Huashan Sun , Yizhe Yang , Yinghao Li , Jiawei Li , Yang Gao

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

Computation and Language · Computer Science 2020-12-15 Fei Yuan , Linjun Shou , Jian Pei , Wutao Lin , Ming Gong , Yan Fu , Daxin Jiang

Data-free knowledge distillation (DFKD) aims to obtain a lightweight student model without original training data. Existing works generally synthesize data from the pre-trained teacher model to replace the original training data for student…

Computer Vision and Pattern Recognition · Computer Science 2023-07-11 Shiya Luo , Defang Chen , Can Wang

Continual learning aims to rapidly and continually learn the current task from a sequence of tasks. Compared to other kinds of methods, the methods based on experience replay have shown great advantages to overcome catastrophic forgetting.…

Machine Learning · Computer Science 2022-09-14 Ya-nan Han , Jian-wei Liu

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Jialiang Tang , Shuo Chen , Chen Gong

Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a central obstacle. Among continual learning methods, regularization-based approaches are…

Machine Learning · Computer Science 2026-05-26 Mingxu Zhang , Yuhan Li , Lujundong Li , Dazhong Shen , Hui Xiong , Ying Sun

Supervised Fine-Tuning (SFT) is a critical step for enhancing the instruction-following capabilities of Large Language Models (LLMs) and adapting them to specialized domains. However, SFT often leads to a degradation of the model's general…

Computation and Language · Computer Science 2025-07-01 Fei Ding , Baiqiao Wang

One of the major limitations of deep learning models is that they face catastrophic forgetting in an incremental learning scenario. There have been several approaches proposed to tackle the problem of incremental learning. Most of these…

Machine Learning · Computer Science 2021-02-04 Vinod K Kurmi , Badri N. Patro , Venkatesh K. Subramanian , Vinay P. Namboodiri

Neural fields are increasingly used as a light-weight, continuous, and differentiable signal representation in (bio)medical imaging. However, unlike discrete signal representations such as voxel grids, neural fields cannot be easily…

Image and Video Processing · Electrical Eng. & Systems 2026-01-21 Wouter Visser , Jelmer M. Wolterink

Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to…

Machine Learning · Computer Science 2023-01-31 Aref Jafari , Mehdi Rezagholizadeh , Ali Ghodsi

Memory-efficient transfer learning (METL) approaches have recently achieved promising performance in adapting pre-trained models to downstream tasks. They avoid applying gradient backpropagation in large backbones, thus significantly…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Yutong Zhang , Jiaxin Chen , Honglin Chen , Kaiqi Zheng , Shengcai Liao , Hanwen Zhong , Weixin Li , Yunhong Wang

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Computer Vision and Pattern Recognition · Computer Science 2021-01-22 Umberto Michieli , Pietro Zanuttigh

In the telephony scenarios, the fake speech detection (FSD) task to combat speech spoofing attacks is challenging. Data augmentation (DA) methods are considered effective means to address the FSD task in telephony scenarios, typically…

Sound · Computer Science 2024-06-17 Cunhang Fan , Shunbo Dong , Jun Xue , Yujie Chen , Jiangyan Yi , Zhao Lv

Traditional object detectors are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will lead to catastrophic forgetting. Knowledge distillation is a flexible way to…

Computer Vision and Pattern Recognition · Computer Science 2022-04-06 Tao Feng , Mang Wang , Hangjie Yuan

Large Language Models (LLMs) have achieved remarkable success, underpinning diverse AI applications. However, they often suffer from performance degradation due to factors such as catastrophic forgetting during Supervised Fine-Tuning (SFT),…

Machine Learning · Computer Science 2026-04-20 Chi Liu , Xin Chen , Xu Zhou , Fangbo Tu , Srinivasan Manoharan

The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previously learned concepts…

Machine Learning · Computer Science 2019-07-08 Huaiyu Li , Weiming Dong , Bao-Gang Hu

In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 K J Joseph , Jathushan Rajasegaran , Salman Khan , Fahad Shahbaz Khan , Vineeth N Balasubramanian

Knowledge Distillation (KD) is a common method for transferring the ``knowledge'' learned by one machine learning model (the \textit{teacher}) into another model (the \textit{student}), where typically, the teacher has a greater capacity…

Machine Learning · Computer Science 2020-04-21 Jie Fu , Xue Geng , Zhijian Duan , Bohan Zhuang , Xingdi Yuan , Adam Trischler , Jie Lin , Chris Pal , Hao Dong