Federated learning is a specific distributed learning paradigm in which a central server aggregates updates from multiple clients' local models, thereby enabling the server to learn without requiring clients to upload their private data, maintaining data privacy. While existing federated learning methods are primarily designed for static data, real-world applications often require clients to learn new categories over time. This challenge necessitates the integration of continual learning techniques, leading to federated continual learning (FCL). To address both catastrophic forgetting and non-IID issues, we propose to use masked autoencoders (MAEs) as parameter-efficient federated continual learners, called pMAE. pMAE learns reconstructive prompt on the client side through image reconstruction using MAE. On the server side, it reconstructs the uploaded restore information to capture the data distribution across previous tasks and different clients, using these reconstructed images to fine-tune discriminative prompt and classifier parameters tailored for classification, thereby alleviating catastrophic forgetting and non-IID issues on a global scale. Experimental results demonstrate that pMAE achieves performance comparable to existing prompt-based methods and can enhance their effectiveness, particularly when using self-supervised pre-trained transformers as the backbone. Code is available at: https://github.com/ycheoo/pMAE.
Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
National Key Laboratory for Multimedia Information Processing（多媒体信息处理国家重点实验室）；School of Computer Science（计算机学院）；Peking University（北京大学）；CUHK（香港中文大学）；University of Science Technology of China（中国科学技术大学）
In the SSLAD-Track 3B challenge on continual learning, we propose the method of COntinual Learning with Transformer (COLT). We find that transformers suffer less from catastrophic forgetting compared to convolutional neural network. The major principle of our method is to equip the transformer based feature extractor with old knowledge distillation and head expanding strategies to compete catastrophic forgetting. In this report, we first introduce the overall framework of continual learning for object detection. Then, we analyse the key elements' effect on withstanding catastrophic forgetting …
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Australian National University（澳大利亚国立大学）；Monash University（莫纳什大学）；Linköping University（林雪平大学）
The continual learning setting aims to learn new tasks over time without forgetting the previous ones. The literature reports several significant efforts to tackle this problem with limited or no access to previous task data. Among such efforts, typical solutions offer sophisticated techniques involving memory replay, knowledge distillation, model regularization, and dynamic network expansion. The resulting methods have a retraining cost at each learning task, dedicated memory requirements, and setting-specific design choices. In this work, we show that a frozen CLIP (Contrastive Language-Imag…
Continual Self-Supervised Learning with Masked Autoencoders in Remote Sensing
Faculty of Electrical Engineering and Computer Science, Technische Universität Berlin（电气工程与计算机科学学院，柏林技术大学）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）
University of Trento（特伦托大学）；Inria（法国国家信息与自动化研究所）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale. However, their efficacy is catastrophically reduced in a Continual Learning (CL) scenario where data is presented to the model sequentially. In this paper, we show that self-supervised loss functions can be seamlessly converted into distillation mechanisms for CL by adding a predictor network that maps the current state of the representations to their past state. This enables us to devise a framework for Continual self…
Eindhoven University of Technology（埃因霍温理工大学）；University of Twente（特文特大学）
Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn in non-stationary distributions. In most settings of the current approaches, the agent starts from randomly initialized parameters and is optimized to master the current task regardless of the usefulness of the learned representation for future tasks. Moreover, each of the future tasks uses all the previously learned knowledge although parts of this knowledg…
SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
University of Technology Sydney（悉尼科技大学）；Tsinghua University（清华大学）；Beihang University（北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；Beijing Jiaotong University（北京交通大学）
Toyota Motor Europe（丰田汽车欧洲公司）；University of Cambridge（剑桥大学）
Novelty Detection methods identify samples that are not representative of a model's training set thereby flagging misleading predictions and bringing a greater flexibility and transparency at deployment time. However, research in this area has only considered Novelty Detection in the offline setting. Recently, there has been a growing realization in the computer vision community that applications demand a more flexible framework - Continual Learning - where new batches of data representing new domains, new classes or new tasks become available at different points in time. In this setting, Nove…
Targeted for real world scenarios, online continual learning aims to learn new tasks from sequentially available data under the condition that each data is observed only once by the learner. Though recent works have made remarkable achievements by storing part of learned task data as exemplars for knowledge replay, the performance is greatly relied on the size of stored exemplars while the storage consumption is a significant constraint in continual learning. In addition, storing exemplars may not always be feasible for certain applications due to privacy concerns. In this work, we propose a n…
Computer Vision Center (CVC)（计算机视觉中心）；Universitat Autonoma of Barcelona (UAB)（巴塞罗那自治大学）；Media Integration and Communication Center（媒体整合与传播中心）
Recent self-supervised learning methods are able to learn high-quality image representations and are closing the gap with supervised approaches. However, these methods are unable to acquire new knowledge incrementally -- they are, in fact, mostly used only as a pre-training phase over IID data. In this work we investigate self-supervised methods in continual learning regimes without any replay mechanism. We show that naive functional regularization, also known as feature distillation, leads to lower plasticity and limits continual learning performance. Instead, we propose Projected Functional …
Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior results than image replay, while requiring less memory. Quantized exemplars can further reduce the memory usage. However, a drawback of these methods is that they use a fixed (or very intransigent) b…
National Taiwan University（台湾大学）；Academia Sinica（中央研究院）；ucfunnel Co. Ltd.（ucfunnel有限公司）
In visual search, the gallery set could be incrementally growing and added to the database in practice. However, existing methods rely on the model trained on the entire dataset, ignoring the continual updating of the model. Besides, as the model updates, the new model must re-extract features for the entire gallery set to maintain compatible feature space, imposing a high computational cost for a large gallery set. To address the issues of long-term visual search, we introduce a continual learning (CL) approach that can handle the incrementally growing gallery set with backward embedding cons…
Self-paced Weight Consolidation for Continual Learning
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Vanderbilt University（范德堡大学）；University of California, Davis（加州大学戴维斯分校）
Continual and multi-task learning are common machine learning approaches to learning from multiple tasks. The existing works in the literature often assume multi-task learning as a sensible performance upper bound for various continual learning algorithms. While this assumption is empirically verified for different continual learning benchmarks, it is not rigorously justified. Moreover, it is imaginable that when learning from multiple tasks, a small subset of these tasks could behave as adversarial tasks reducing the overall learning performance in a multi-task setting. In contrast, continual…
Duke University（杜克大学）；Samsung Semiconductor Inc.（三星半导体公司）
Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. However, since current works tend to assume exclusivity or dissimilarity among learning tasks, these methods require constantly accumulating task-specific knowledge in memory for each task. This results in the eventual prohibitive expansion of the knowledge repository if we consider learning from a long sequence of tasks. In this work, we introduce a paradigm where the continual learner gets a sequence of mixed simila…
Computer Vision Center, UAB（巴塞罗那自治大学计算机视觉中心）；Huawei（华为）
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 of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive seq…
Rochester Institute of Technology（罗切斯特理工学院）；Paige；Cornell Tech（康奈尔科技学院）
In continual learning, a system learns from non-stationary data streams or batches without catastrophic forgetting. While this problem has been heavily studied in supervised image classification and reinforcement learning, continual learning in neural networks designed for abstract reasoning has not yet been studied. Here, we study continual learning of analogical reasoning. Analogical reasoning tests such as Raven's Progressive Matrices (RPMs) are commonly used to measure non-verbal abstract reasoning in humans, and recently offline neural networks for the RPM problem have been proposed. In t…
Deep learning has thrived by training on large-scale datasets. However, in robotics applications sample efficiency is critical. We propose a novel adaptive masked proxies method that constructs the final segmentation layer weights from few labelled samples. It utilizes multi-resolution average pooling on base embeddings masked with the label to act as a positive proxy for the new class, while fusing it with the previously learned class signatures. Our method is evaluated on PASCAL-$5^i$ dataset and outperforms the state-of-the-art in the few-shot semantic segmentation. Unlike previous methods,…
University of Tübingen（图宾根大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Large pre-trained, zero-shot capable models have shown considerable success both for standard transfer and adaptation tasks, with particular robustness towards distribution shifts. In addition, subsequent fine-tuning can considerably improve performance on a selected downstream task. However, through naive fine-tuning, these zero-shot models lose their generalizability and robustness towards distribution shifts. This is a particular problem for tasks such as Continual Learning (CL), where continuous adaptation has to be performed as new task distributions are introduced sequentially. In this w…
Both few-shot and continual learning have seen substantial progress in the last years due to the introduction of proper benchmarks. That being said, the field has still to frame a suite of benchmarks for the highly desirable setting of continual few-shot learning, where the learner is presented a number of few-shot tasks, one after the other, and then asked to perform well on a validation set stemming from all previously seen tasks. Continual few-shot learning has a small computational footprint and is thus an excellent setting for efficient investigation and experimentation. In this paper we …
Sharif University of Technology（谢里夫理工大学）；USC Viterbi School of Engineering（南加州大学维特比工程学院）
The existing continual learning methods are mainly focused on fully-supervised scenarios and are still not able to take advantage of unlabeled data available in the environment. Some recent works tried to investigate semi-supervised continual learning (SSCL) settings in which the unlabeled data are available, but it is only from the same distribution as the labeled data. This assumption is still not general enough for real-world applications and restricts the utilization of unsupervised data. In this work, we introduce Open-Set Semi-Supervised Continual Learning (OSSCL), a more realistic semi-…
Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streaming data proves a challenging endeavor as they rapidly become outdated, caused by an ever-changing parameter space during the learning process. Additionally, continual learning does not assume the data stream to be stationary, typically resulting in catastrophic forgetting of previous knowledge. As a first, we introduce a system addressing both problems, where prototypes evolve continually in a shared latent space, enabling learning and…
Ca’ Foscari University（威尼斯福斯卡里大学）；University of New South Wales（新南威尔士大学）；Computer Vision Center（计算机视觉中心）
In this paper, we investigate the continual learning of Vision Transformers (ViT) for the challenging exemplar-free scenario, with special focus on how to efficiently distill the knowledge of its crucial self-attention mechanism (SAM). Our work takes an initial step towards a surgical investigation of SAM for designing coherent continual learning methods in ViTs. We first carry out an evaluation of established continual learning regularization techniques. We then examine the effect of regularization when applied to two key enablers of SAM: (a) the contextualized embedding layers, for their abi…
Vanderbilt University（范德堡大学）；University of California, Davis（加州大学戴维斯分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
Continual/lifelong learning from a non-stationary input data stream is a cornerstone of intelligence. Despite their phenomenal performance in a wide variety of applications, deep neural networks are prone to forgetting their previously learned information upon learning new ones. This phenomenon is called "catastrophic forgetting" and is deeply rooted in the stability-plasticity dilemma. Overcoming catastrophic forgetting in deep neural networks has become an active field of research in recent years. In particular, gradient projection-based methods have recently shown exceptional performance at…
This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core designs. First, we develop an asymmetric encoder-decoder architecture, with an encoder that operates only on the visible subset of patches (without mask tokens), along with a lightweight decoder that reconstructs the original image from the latent representation and mask tokens. Second, we find that masking a high proportion of the input image, e.g., 75%, yield…
SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training
Australian Artificial Intelligence Institute（澳大利亚人工智能研究所）；University of Technology Sydney（悉尼科技大学）；Tsinghua University（清华大学）；Beihang University（北京航空航天大学）；Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）
Concatenated Masked Autoencoders as Spatial-Temporal Learner
Meetyou AI Lab（美图AI实验室）；Institute for Datability Science, Osaka University（大阪大学数据科学研究所）；Qufu Normal University（曲阜师范大学）；East China Jiaotong University（华东交通大学）
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；Tsinghua University（清华大学）
Nanjing University（南京大学）；Tencent AI Lab（腾讯人工智能实验室）；Shanghai AI Lab（上海人工智能实验室）
Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners for self-supervised video pre-training (SSVP). We are inspired by the recent ImageMAE and propose customized video tube masking with an extremely high ratio. This simple design makes video reconstruction a more challenging self-supervision task, thus encouraging extracting more effective video representations during this pre-training process. We obtain three i…
Masked Motion Predictors are Strong 3D Action Representation Learners
University of Science and Technology of China（中国科学技术大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；The University of Sydney（悉尼大学）；Merchants Union Consumer Finance Company Limited（招商局消费金融有限公司）
Christian Doppler Laboratory for Embedded Machine Learning（克里斯蒂安·多普勒嵌入式机器学习实验室）；Graz University of Technology（格拉茨工业大学）；Southeast University（东南大学）；Korea Advanced Institute of Science and Technology (KAIST)（韩国高等科学技术研究院（KAIST））
Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data. Like existing TTT methods from the 2D image domain, MATE also leverages test data for adaptation. Its test-time objective is that of a Masked Autoencoder: a large portion of each test point cloud is removed before it is fed to the network, tasked with reconstructing the full point cloud. Once the network is updated, it is used to classify the point cloud. We test MATE on several 3D object classificatio…
This paper studies a conceptually simple extension of Masked Autoencoders (MAE) to spatiotemporal representation learning from videos. We randomly mask out spacetime patches in videos and learn an autoencoder to reconstruct them in pixels. Interestingly, we show that our MAE method can learn strong representations with almost no inductive bias on spacetime (only except for patch and positional embeddings), and spacetime-agnostic random masking performs the best. We observe that the optimal masking ratio is as high as 90% (vs. 75% on images), supporting the hypothesis that this ratio is related…
Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation
University of Science and Technology of China (USTC)（中国科学技术大学）；Suzhou Institute for Advanced Research, USTC（中国科学技术大学苏州高等研究院）；Stanford University（斯坦福大学）；State Key Laboratory of Precision and Intelligent Chemistry, USTC（中国科学技术大学精准与智能化学国家重点实验室）；Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS（中国科学院计算技术研究所中国科学院智能信息处理重点实验室）
Vision Transformer (ViT) suffers from data scarcity in semi-supervised learning (SSL). To alleviate this issue, inspired by masked autoencoder (MAE), which is a data-efficient self-supervised learner, we propose Semi-MAE, a pure ViT-based SSL framework consisting of a parallel MAE branch to assist the visual representation learning and make the pseudo labels more accurate. The MAE branch is designed as an asymmetric architecture consisting of a lightweight decoder and a shared-weights encoder. We feed the weakly-augmented unlabeled data with a high masking ratio to the MAE branch and reconstru…
