English
Related papers

Related papers: Adapter Incremental Continual Learning of Efficien…

200 papers

Audio event has a hierarchical architecture in both time and frequency and can be grouped together to construct more abstract semantic audio classes. In this work, we develop a multiscale audio spectrogram Transformer (MAST) that employs…

Sound · Computer Science 2023-03-21 Wentao Zhu , Mohamed Omar

Task-incremental continual learning refers to continually training a model in a sequence of tasks while overcoming the problem of catastrophic forgetting (CF). The issue arrives for the reason that the learned representations are forgotten…

Machine Learning · Computer Science 2023-05-23 Yun Luo , Xiaotian Lin , Zhen Yang , Fandong Meng , Jie Zhou , Yue Zhang

This paper proposes a simple but highly efficient expansion-based model for continual learning. The recent feature transformation, masking and factorization-based methods are efficient, but they grow the model only over the global or shared…

Machine Learning · Computer Science 2023-12-05 Soumya Roy , Vinay K Verma , Deepak Gupta

Neural networks encounter the challenge of Catastrophic Forgetting (CF) in continual learning, where new task learning interferes with previously learned knowledge. Existing data fine-tuning and regularization methods necessitate task…

Machine Learning · Computer Science 2024-05-17 Yuwei Sun , Ippei Fujisawa , Arthur Juliani , Jun Sakuma , Ryota Kanai

Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online…

Machine Learning · Computer Science 2026-02-24 Sarthak Kumar Maharana , Akshay Mehra , Bhavya Ramakrishna , Yunhui Guo , Guan-Ming Su

Continual Learning (CL) in Automatic Speech Recognition (ASR) suffers from catastrophic forgetting when adapting to new tasks, domains, or speakers. A common strategy to mitigate this is to store a subset of past data in memory for…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-06 Steven Vander Eeckt , Hugo Van hamme

We develop a novel approach for confidently accelerating inference in the large and expensive multilayer Transformers that are now ubiquitous in natural language processing (NLP). Amortized or approximate computational methods increase…

Computation and Language · Computer Science 2021-09-10 Tal Schuster , Adam Fisch , Tommi Jaakkola , Regina Barzilay

Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context…

Computation and Language · Computer Science 2024-10-23 Tsachi Blau , Moshe Kimhi , Yonatan Belinkov , Alexander Bronstein , Chaim Baskin

The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…

Computation and Language · Computer Science 2022-10-27 Xulong Zhang , Jianzong Wang , Ning Cheng , Mengyuan Zhao , Zhiyong Zhang , Jing Xiao

Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be…

Machine Learning · Computer Science 2020-03-27 Jathushan Rajasegaran , Salman Khan , Munawar Hayat , Fahad Shahbaz Khan , Mubarak Shah

Task Free online continual learning (TF-CL) is a challenging problem where the model incrementally learns tasks without explicit task information. Although training with entire data from the past, present as well as future is considered as…

Machine Learning · Computer Science 2024-02-20 Byung Hyun Lee , Min-hwan Oh , Se Young Chun

Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending…

Sound · Computer Science 2022-02-14 Yuan Gong , Cheng-I Jeff Lai , Yu-An Chung , James Glass

The recently proposed Conformer architecture has shown state-of-the-art performances in Automatic Speech Recognition by combining convolution with attention to model both local and global dependencies. In this paper, we study how to reduce…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-09 Maxime Burchi , Valentin Vielzeuf

Continual learning necessitates the continual adaptation of models to newly emerging tasks while minimizing the catastrophic forgetting of old ones. This is extremely challenging for large language models (LLMs) with vanilla full-parameter…

Computation and Language · Computer Science 2024-10-28 Chenyang Song , Xu Han , Zheni Zeng , Kuai Li , Chen Chen , Zhiyuan Liu , Maosong Sun , Tao Yang

As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critical. Methods incorporating network expansion have shown…

Machine Learning · Computer Science 2021-03-26 Vinay Kumar Verma , Kevin J Liang , Nikhil Mehta , Piyush Rai , Lawrence Carin

Continual learning (CL) is a paradigm that aims to replicate the human ability to learn and accumulate knowledge continually without forgetting previous knowledge and transferring it to new tasks. Recent instruction tuning (IT) involves…

Computation and Language · Computer Science 2023-10-24 Zihan Zhang , Meng Fang , Ling Chen , Mohammad-Reza Namazi-Rad

Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In this work, we identify attention drift in Vision Transformers…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Yue Lu , Xiangyu Zhou , Shizhou Zhang , Yinghui Xing , Guoqiang Liang , Wencong Zhang

Continual learning (CL) enables models to adapt to evolving data streams without catastrophic forgetting, a fundamental requirement for real-world AI systems. However, the current methods often depend on large replay buffers or heavily…

Machine Learning · Computer Science 2025-11-14 Indu Solomon , Aye Phyu Phyu Aung , Uttam Kumar , Senthilnath Jayavelu

We introduce EfficientCL, a memory-efficient continual pretraining method that applies contrastive learning with novel data augmentation and curriculum learning. For data augmentation, we stack two types of operation sequentially: cutoff…

Computation and Language · Computer Science 2021-10-19 Seonghyeon Ye , Jiseon Kim , Alice Oh

Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions, addressing real-world dynamism. Existing CTTA methods mainly rely on entropy minimization or…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Jiaming Liu , Ran Xu , Senqiao Yang , Renrui Zhang , Qizhe Zhang , Zehui Chen , Yandong Guo , Shanghang Zhang