English
Related papers

Related papers: DyTox: Transformers for Continual Learning with DY…

200 papers

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity…

Computer Vision and Pattern Recognition · Computer Science 2021-04-19 Matthias De Lange , Rahaf Aljundi , Marc Masana , Sarah Parisot , Xu Jia , Ales Leonardis , Gregory Slabaugh , Tinne Tuytelaars

Convolution neural networks (CNNs) and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Yangyang Xu , Yibo Yang , Lefei Zhang

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer…

Computation and Language · Computer Science 2024-02-07 Aydar Bulatov , Yuri Kuratov , Yermek Kapushev , Mikhail S. Burtsev

We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from…

Computer Vision and Pattern Recognition · Computer Science 2016-12-12 Hang Zhang , Jia Xue , Kristin Dana

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…

Machine Learning · Computer Science 2025-08-19 Parsa Omidi , Xingshuai Huang , Axel Laborieux , Bahareh Nikpour , Tianyu Shi , Armaghan Eshaghi

Continual VideoQA with multimodal LLMs is hindered by interference between tasks and the prohibitive cost of storing task-specific prompts. We introduce HyperTokens, a transformer-based token generator that produces fine-tuning tokens on…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Toan Nguyen , Yang Liu , Celso De Melo , Flora D. Salim

Adapting pre-trained models to specialized tasks often leads to catastrophic forgetting, where new knowledge overwrites foundational capabilities. Existing methods either compromise performance on the new task or struggle to balance…

Machine Learning · Computer Science 2026-03-10 Dyah Adila , Hanna Mazzawi , Benoit Dherin , Xavier Gonzalvo

Diffusion models have achieved remarkable success in image and video generation. In this work, we demonstrate that diffusion models can also \textit{generate high-performing neural network parameters}. Our approach is simple, utilizing an…

Machine Learning · Computer Science 2025-01-03 Kai Wang , Dongwen Tang , Boya Zeng , Yida Yin , Zhaopan Xu , Yukun Zhou , Zelin Zang , Trevor Darrell , Zhuang Liu , Yang You

In the domain of computer vision, deep residual neural networks like EfficientNet have set new standards in terms of robustness and accuracy. One key problem underlying the training of deep neural networks is the immanent lack of a…

Computer Vision and Pattern Recognition · Computer Science 2022-02-22 Raoul Schönhof , Jannes Elstner , Radu Manea , Steffen Tauber , Ramez Awad , Marco F. Huber

Transformer-based neural networks have surpassed promising performance on many biomedical image segmentation tasks due to a better global information modeling from the self-attention mechanism. However, most methods are still designed for…

Computer Vision and Pattern Recognition · Computer Science 2023-02-02 Zheyuan Zhang , Ulas Bagci

Recent advancements in imitation learning have led to transformer-based behavior foundation models (BFMs) that enable multi-modal, human-like control for humanoid agents. While excelling at zero-shot generation of robust behaviors, BFMs…

Machine Learning · Computer Science 2026-03-30 Ron Vainshtein , Zohar Rimon , Shie Mannor , Chen Tessler

Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This ability is limited in the current deep neural networks by a…

Machine Learning · Computer Science 2018-06-20 Risto Vuorio , Dong-Yeon Cho , Daejoong Kim , Jiwon Kim

Over the past decade, Deep Convolutional Neural Networks (DCNNs) have shown remarkable performance in most computer vision tasks. These tasks traditionally use a fixed dataset, and the model, once trained, is deployed as is. Adding new…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Deboleena Roy , Priyadarshini Panda , Kaushik Roy

Many different deep networks have been used to approximate, accelerate or improve traditional image operators. Among these traditional operators, many contain parameters which need to be tweaked to obtain the satisfactory results, which we…

Computer Vision and Pattern Recognition · Computer Science 2019-07-15 Qingnan Fan , Dongdong Chen , Lu Yuan , Gang Hua , Nenghai Yu , Baoquan Chen

Domain adaptation aims at training a classifier in one dataset and applying it to a related but not identical dataset. One successfully used framework of domain adaptation is to learn a transformation to match both the distribution of the…

Computer Vision and Pattern Recognition · Computer Science 2015-03-03 Xu Zhang , Felix Xinnan Yu , Shih-Fu Chang , Shengjin Wang

Pre-trained representation is one of the key elements in the success of modern deep learning. However, existing works on continual learning methods have mostly focused on learning models incrementally from scratch. In this paper, we explore…

Machine Learning · Computer Science 2022-08-18 Hyounguk Shon , Janghyeon Lee , Seung Hwan Kim , Junmo Kim

Transformers in their common form are inherently limited to operate on whole token sequences rather than on one token at a time. Consequently, their use during online inference on time-series data entails considerable redundancy due to the…

Artificial Intelligence · Computer Science 2023-06-28 Lukas Hedegaard , Arian Bakhtiarnia , Alexandros Iosifidis

This paper studies a new design of the optimization algorithm for training deep learning models with a fixed architecture of the classification network in a continual learning framework. The training data is non-stationary and the…

Machine Learning · Computer Science 2022-07-05 Yunfei Teng , Anna Choromanska , Murray Campbell , Songtao Lu , Parikshit Ram , Lior Horesh

Diffusion models have achieved state-of-the-art synthesis quality on both visual and audio tasks, and recent works further adapt them to textual data by diffusing on the embedding space. In this paper, we conduct systematic studies of the…

Computation and Language · Computer Science 2024-04-23 Zhujin Gao , Junliang Guo , Xu Tan , Yongxin Zhu , Fang Zhang , Jiang Bian , Linli Xu

Multi-task learning of dense prediction tasks, by sharing both the encoder and decoder, as opposed to sharing only the encoder, provides an attractive front to increase both accuracy and computational efficiency. When the tasks are similar,…

Computer Vision and Pattern Recognition · Computer Science 2022-08-22 Naresh Kumar Gurulingan , Elahe Arani , Bahram Zonooz