English
Related papers

Related papers: PLATE: Plasticity-Tunable Efficient Adapters for G…

200 papers

In finetuning a large pretrained model to downstream tasks, parameter-efficient fine-tuning (PEFT) methods can effectively finetune pretrained models with few trainable parameters, but suffer from high GPU memory consumption and slow…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Ningyuan Tang , Minghao Fu , Ke Zhu , Jianxin Wu

Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying pretrained model is updated or retrained (e.g., on larger and more curated datasets), the fine-tuned model…

To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collectively known as general continual learning (GCL),…

Artificial Intelligence · Computer Science 2026-05-12 Guanglong Sun , Hongwei Yan , Liyuan Wang , Zhiqi Kang , Shuang Cui , Hang Su , Jun Zhu , Yi Zhong

Parameter-Efficient Fine-Tuning (PEFT) effectively adapts pre-trained transformers to downstream tasks. However, the optimization of tasks performance often comes at the cost of generalizability in fine-tuned models. To address this issue,…

Machine Learning · Computer Science 2026-03-09 Yao Ni , Shan Zhang , Piotr Koniusz

Continual learning requires the model to learn multiple tasks sequentially. In continual learning, the model should possess the ability to maintain its performance on old tasks (stability) and the ability to adapt to new tasks continuously…

Machine Learning · Computer Science 2024-04-04 Yan-Shuo Liang , Wu-Jun Li

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…

Computer Vision and Pattern Recognition · Computer Science 2019-09-20 Tasfia Shermin , Shyh Wei Teng , Manzur Murshed , Guojun Lu , Ferdous Sohel , Manoranjan Paul

Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Da-Wei Zhou , Hai-Long Sun , Han-Jia Ye , De-Chuan Zhan

Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge. Motivated by the characteristics of neural networks, in which information is stored in weights on connections, we investigated…

Machine Learning · Computer Science 2023-06-21 Depeng Li , Tianqi Wang , Bingrong Xu , Kenji Kawaguchi , Zhigang Zeng , Ponnuthurai Nagaratnam Suganthan

Continual learning algorithms strive to acquire new knowledge while preserving prior information. Often, these algorithms emphasise stability and restrict network updates upon learning new tasks. In many cases, such restrictions come at a…

Machine Learning · Computer Science 2024-06-21 Daniel Anthes , Sushrut Thorat , Peter König , Tim C. Kietzmann

A continual learning agent builds on previous experiences to develop increasingly complex behaviors by adapting to non-stationary and dynamic environments while preserving previously acquired knowledge. However, scaling these systems…

Machine Learning · Computer Science 2025-03-06 Achref Jaziri , Etienne Künzel , Visvanathan Ramesh

As deep neural networks evolve from convolutional neural networks (ConvNets) to advanced vision transformers (ViTs), there is an increased need to eliminate redundant data for faster processing without compromising accuracy. Previous…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Tanvir Mahmud , Burhaneddin Yaman , Chun-Hao Liu , Diana Marculescu

Large-scale pretrained models have proven immensely valuable in handling data-intensive modalities like text and image. However, fine-tuning these models for certain specialized modalities, such as protein sequence and cosmic ray, poses…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Lincan Cai , Shuang Li , Wenxuan Ma , Jingxuan Kang , Binhui Xie , Zixun Sun , Chengwei Zhu

In this work, we study the problem of how to leverage instructional videos to facilitate the understanding of human decision-making processes, focusing on training a model with the ability to plan a goal-directed procedure from real-world…

Robotics · Computer Science 2022-03-11 Jiankai Sun , De-An Huang , Bo Lu , Yun-Hui Liu , Bolei Zhou , Animesh Garg

The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity…

Computation and Language · Computer Science 2024-01-12 Jianwei Li , Qi Lei , Wei Cheng , Dongkuan Xu

Continual learning (CL) is crucial for evaluating adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forgetting, where models lose proficiency in previously learned tasks as they…

The workflow of pretraining and fine-tuning has emerged as a popular paradigm for solving various NLP and V&L (Vision-and-Language) downstream tasks. With the capacity of pretrained models growing rapidly, how to perform parameter-efficient…

Computation and Language · Computer Science 2022-03-09 Zhengkun Zhang , Wenya Guo , Xiaojun Meng , Yasheng Wang , Yadao Wang , Xin Jiang , Qun Liu , Zhenglu Yang

In recent years, Deep Learning models have shown a great performance in complex optimization problems. They generally require large training datasets, which is a limitation in most practical cases. Transfer learning allows importing the…

Neural and Evolutionary Computing · Computer Science 2024-02-06 Javier Poyatos , Daniel Molina , Aritz. D. Martinez , Javier Del Ser , Francisco Herrera

In this paper, we propose a novel network training mechanism called "dynamic channel propagation" to prune the neural networks during the training period. In particular, we pick up a specific group of channels in each convolutional layer to…

Computer Vision and Pattern Recognition · Computer Science 2020-07-06 Shibo Shen , Rongpeng Li , Zhifeng Zhao , Honggang Zhang , Yugeng Zhou

Reinforcement learning (RL) has demonstrated remarkable capability in acquiring robot skills, but learning each new skill still requires substantial data collection for training. The pretrain-and-finetune paradigm offers a promising…

Robotics · Computer Science 2025-03-25 Ziang Zheng , Guojian Zhan , Bin Shuai , Shengtao Qin , Jiangtao Li , Tao Zhang , Shengbo Eben Li

Adapting large pre-trained models to unseen tasks under tight data and compute budgets remains challenging. Meta-learning approaches explicitly learn good initializations, but they require an additional meta-training phase over many tasks,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Junghwan Park , Woojin Cho , Junhyuk Heo , Darongsae Kwon , Kookjin Lee