English
Related papers

Related papers: Integrating Task-Specific and Universal Adapters f…

200 papers

Class incremental learning (CIL) trains a network on sequential tasks with separated categories in each task but suffers from catastrophic forgetting, where models quickly lose previously learned knowledge when acquiring new tasks. The…

Machine Learning · Computer Science 2024-11-05 Huiping Zhuang , Yizhu Chen , Di Fang , Run He , Kai Tong , Hongxin Wei , Ziqian Zeng , Cen Chen

Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly, achieving better per-task performance with fewer parameters than single-task learning. Recently, decoder-focused architectures have…

Computer Vision and Pattern Recognition · Computer Science 2024-11-07 Dimitrios Sinodinos , Narges Armanfard

Task-incremental learning involves the challenging problem of learning new tasks continually, without forgetting past knowledge. Many approaches address the problem by expanding the structure of a shared neural network as tasks arrive, but…

Machine Learning · Computer Science 2020-11-24 Azhar Shaikh , Nishant Sinha

Incremental Learning (IL) aims to learn new tasks while preserving previously acquired knowledge. Integrating the zero-shot learning capabilities of pre-trained vision-language models into IL methods has marked a significant advancement.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Haihua Luo , Xuming Ran , Jiangrong Shen , Timo Hämäläinen , Zhonghua Chen , Qi Xu , Fengyu Cong

Fine-tuning large pre-trained language models for downstream tasks remains a critical challenge in natural language processing. This paper presents an empirical analysis comparing two efficient fine-tuning methods - BitFit and adapter…

Machine Learning · Computer Science 2024-01-09 Nigel Doering , Cyril Gorlla , Trevor Tuttle , Adhvaith Vijay

Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data while retaining learned knowledge. A major challenge of CIL arises when applying to real-world data characterized by non-uniform…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Jiangpeng He , Fengqing Zhu

Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time while retaining previously acquired knowledge. Recently, Parameter-Efficient Fine-Tuning (PEFT)…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Huaijie Wang , De Cheng , Lingfeng He , Yan Li , Jie Li , Nannan Wang , Xinbo Gao

In-context learning (ICL) allows transformer-based language models that are pre-trained on general text to quickly learn a specific task with a few "task demonstrations" without updating their parameters, significantly boosting their…

Computation and Language · Computer Science 2024-12-17 Zijian Zhou , Xiaoqiang Lin , Xinyi Xu , Alok Prakash , Daniela Rus , Bryan Kian Hsiang Low

Large language models (LLM) have recently shown the extraordinary ability to perform unseen tasks based on few-shot examples provided as text, also known as in-context learning (ICL). While recent works have attempted to understand the…

Computation and Language · Computer Science 2024-04-05 Harmon Bhasin , Timothy Ossowski , Yiqiao Zhong , Junjie Hu

Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and…

Machine Learning · Computer Science 2022-04-22 Jonathan Pilault , Amine Elhattami , Christopher Pal

Class-Incremental Learning (CIL) is a critical capability for real-world applications, enabling learning systems to adapt to new tasks while retaining knowledge from previous ones. Recent advancements in pre-trained models (PTMs) have…

Machine Learning · Computer Science 2025-04-28 Kun He , Zijian Song , Shuoxi Zhang , John E. Hopcroft

Class-incremental learning (CIL) aims to recognize new classes incrementally while maintaining the discriminability of old classes. Most existing CIL methods are exemplar-based, i.e., storing a part of old data for retraining. Without…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Fei Zhu , Xu-Yao Zhang , Zhen Cheng , Cheng-Lin Liu

Vision-language models (VLMs) like CLIP have demonstrated remarkable applicability across a variety of downstream tasks, including zero-shot image classification. Recently, the use of prompts or adapters for efficient transfer learning…

Computer Vision and Pattern Recognition · Computer Science 2024-10-14 Yongjin Yang , Jongwoo Ko , Se-Young Yun

Recently, Large Language Models (LLMs) have achieved amazing zero-shot learning performance over a variety of Natural Language Processing (NLP) tasks, especially for text generative tasks. Yet, the large size of LLMs often leads to the high…

Computation and Language · Computer Science 2023-09-21 Yukang Xie , Chengyu Wang , Junbing Yan , Jiyong Zhou , Feiqi Deng , Jun Huang

Continual learning involves training neural networks incrementally for new tasks while retaining the knowledge of previous tasks. However, efficiently fine-tuning the model for sequential tasks with minimal computational resources remains a…

Sound · Computer Science 2024-01-03 Nithish Muthuchamy Selvaraj , Xiaobao Guo , Adams Kong , Bingquan Shen , Alex Kot

Neural Transfer Learning (TL) is becoming ubiquitous in Natural Language Processing (NLP), thanks to its high performance on many tasks, especially in low-resourced scenarios. Notably, TL is widely used for neural domain adaptation to…

Computation and Language · Computer Science 2021-06-10 Sara Meftah , Nasredine Semmar , Youssef Tamaazousti , Hassane Essafi , Fatiha Sadat

Universal Domain Adaptation (UniDA) seeks to transfer knowledge from a labeled source to an unlabeled target domain without assuming any relationship between their label sets, requiring models to classify known samples while rejecting…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Samuel Felipe dos Santos , Tiago Agostinho de Almeida , Jurandy Almeida

Class-Incremental Learning (CIL) enables learning systems to continuously adapt to evolving data streams. With the advancement of pre-training, leveraging pre-trained vision-language models (e.g., CLIP) offers a promising starting point for…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Da-Wei Zhou , Kai-Wen Li , Jingyi Ning , Han-Jia Ye , Lijun Zhang , De-Chuan Zhan

Transformer neural networks are increasingly replacing prior architectures in a wide range of applications in different data modalities. The increasing size and computational demands of fine-tuning large pre-trained transformer neural…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Yuliang Cai , Mohammad Rostami

Large language models (LLMs) like GPT-4 and LLaMA-3 utilize the powerful in-context learning (ICL) capability of Transformer architecture to learn on the fly from limited examples. While ICL underpins many LLM applications, its full…

Machine Learning · Computer Science 2025-03-21 Xingxuan Zhang , Haoran Wang , Jiansheng Li , Yuan Xue , Shikai Guan , Renzhe Xu , Hao Zou , Han Yu , Peng Cui