For real-world applications, robots will need to continually learn in their environments through limited interactions with their users. Toward this, previous works in few-shot class incremental learning (FSCIL) and active class selection (ACS) have achieved promising results but were tested in constrained setups. Therefore, in this paper, we combine ideas from FSCIL and ACS to develop a novel framework that can allow an autonomous agent to continually learn new objects by asking its users to label only a few of the most informative objects in the environment. To this end, we build on a state-of-the-art (SOTA) FSCIL model and extend it with techniques from ACS literature. We term this model Few-shot Incremental Active class SeleCtiOn (FIASco). We further integrate a potential field-based navigation technique with our model to develop a complete framework that can allow an agent to process and reason on its sensory data through the FIASco model, navigate towards the most informative object in the environment, gather data about the object through its sensors and incrementally update the FIASco model. Experimental results on a simulated agent and a real robot show the significance of our approach for long-term real-world robotics applications.
Few-shot class-incremental learning (FSCIL) aims to learn progressively about new classes with very few labeled samples, without forgetting the knowledge of already learnt classes. FSCIL suffers from two major challenges: (i) over-fitting on the new classes due to limited amount of data, (ii) catastrophically forgetting about the old classes due to unavailability of data from these classes in the incremental stages. In this work, we propose a self-supervised stochastic classifier (S3C) to counter both these challenges in FSCIL. The stochasticity of the classifier weights (or class prototypes) not only mitigates the adverse effect of absence of large number of samples of the new classes, but also the absence of samples from previously learnt classes during the incremental steps. This is complemented by the self-supervision component, which helps to learn features from the base classes which generalize well to unseen classes that are encountered in future, thus reducing catastrophic forgetting. Extensive evaluation on three benchmark datasets using multiple evaluation metrics show the effectiveness of the proposed framework. We also experiment on two additional realistic scenarios of FSCIL, namely where the number of annotated data available for each of the new classes can be different, and also where the number of base classes is much lesser, and show that the proposed S3C performs significantly better than the state-of-the-art for all these challenging scenarios.
Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate catastrophic forgetting. In this work, following the recent breakthrough in text-to-image generative models and their wide distribution, we propose the use of a pretrained Stable Diffusion model as a source of additional data for class-incremental learning. Compared to competitive methods that rely on external, often unlabeled, datasets of real images, our approach can generate synthetic samples belonging to the same classes as the previously encountered images. This allows us to use those additional data samples not only in the distillation loss but also for replay in the classification loss. Experiments on the competitive benchmarks CIFAR100, ImageNet-Subset, and ImageNet demonstrate how this new approach can be used to further improve the performance of state-of-the-art methods for class-incremental learning on large scale datasets.
Deep learning models are prone to forgetting information learned in the past when trained on new data. This problem becomes even more pronounced in the context of federated learning (FL), where data is decentralized and subject to independent changes for each user. Continual Learning (CL) studies this so-called \textit{catastrophic forgetting} phenomenon primarily in centralized settings, where the learner has direct access to the complete training dataset. However, applying CL techniques to FL is not straightforward due to privacy concerns and resource limitations. This paper presents a framework for federated class incremental learning that utilizes a generative model to synthesize samples from past distributions instead of storing part of past data. Then, clients can leverage the generative model to mitigate catastrophic forgetting locally. The generative model is trained on the server using data-free methods at the end of each task without requesting data from clients. Therefore, it reduces the risk of data leakage as opposed to training it on the client's private data. We demonstrate significant improvements for the CIFAR-100 dataset compared to existing baselines.
Federated Learning (FL) has been widely concerned for it enables decentralized learning while ensuring data privacy. However, most existing methods unrealistically assume that the classes encountered by local clients are fixed over time. After learning new classes, this assumption will make the model's catastrophic forgetting of old classes significantly severe. Moreover, due to the limitation of communication cost, it is challenging to use large-scale models in FL, which will affect the prediction accuracy. To address these challenges, we propose a novel framework, Federated Enhanced Transformer (FedET), which simultaneously achieves high accuracy and low communication cost. Specifically, FedET uses Enhancer, a tiny module, to absorb and communicate new knowledge, and applies pre-trained Transformers combined with different Enhancers to ensure high precision on various tasks. To address local forgetting caused by new classes of new tasks and global forgetting brought by non-i.i.d (non-independent and identically distributed) class imbalance across different local clients, we proposed an Enhancer distillation method to modify the imbalance between old and new knowledge and repair the non-i.i.d. problem. Experimental results demonstrate that FedET's average accuracy on representative benchmark datasets is 14.1% higher than the state-of-the-art method, while FedET saves 90% of the communication cost compared to the previous method.
This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or classes. At any time, a single model is built that can be applied to predict/classify test instances of any classes learned thus far without providing any task related information for each test instance. Although many techniques have been proposed for CIL, they are mostly empirical. It has been shown recently that a strong CIL system needs a strong within-task prediction (WP) and a strong out-of-distribution (OOD) detection for each task. However, it is still not known whether CIL is actually learnable. This paper shows that CIL is learnable. Based on the theory, a new CIL algorithm is also proposed. Experimental results demonstrate its effectiveness.
Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) setting due to catastrophic forgetting (CF). This paper reports our finding that if we formulate CIL as a continual label generation problem, CF is drastically reduced and the generalizable representations of pre-trained models can be better retained. We thus propose a new CIL method (VAG) that also leverages the sparsity of vocabulary to focus the generation and creates pseudo-replay samples by using label semantics. Experimental results show that VAG outperforms baselines by a large margin.
In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models are challenged by the well-known catastrophic forgetting phenomenon. Typical methods such as rehearsal-based ones rely on storing exemplars of old classes to mitigate catastrophic forgetting, which limits real-world applications considering memory resources and privacy issues. In this paper, we propose a novel rehearsal-free CIL approach that learns continually via the synergy between two Complementary Learning Subnetworks. Our approach involves jointly optimizing a plastic CNN feature extractor and an analytical feed-forward classifier. The inaccessibility of historical data is tackled by holistically controlling the parameters of a well-trained model, ensuring that the decision boundary learned fits new classes while retaining recognition of previously learned classes. Specifically, the trainable CNN feature extractor provides task-dependent knowledge separately without interference; and the final classifier integrates task-specific knowledge incrementally for decision-making without forgetting. In each CIL session, it accommodates new tasks by attaching a tiny set of declarative parameters to its backbone, in which only one matrix per task or one vector per class is kept for knowledge retention. Extensive experiments on a variety of task sequences show that our method achieves competitive results against state-of-the-art methods, especially in accuracy gain, memory cost, training efficiency, and task-order robustness. Furthermore, to make the non-growing backbone (i.e., a model with limited network capacity) suffice to train on more incoming tasks, a graceful forgetting implementation on previously learned trivial tasks is empirically investigated.
Few-shot class-incremental learning (FSCIL) aims to continually learn new classes using a few samples while not forgetting the old classes. The key of this task is effective knowledge transfer from the base session to the incremental sessions. Despite the advance of existing FSCIL methods, the proposed knowledge transfer learning schemes are sub-optimal due to the insufficient optimization for the model's plasticity. To address this issue, we propose a Random Episode Sampling and Augmentation (RESA) strategy that relies on diverse pseudo incremental tasks as agents to achieve the knowledge transfer. Concretely, RESA mimics the real incremental setting and constructs pseudo incremental tasks globally and locally, where the global pseudo incremental tasks are designed to coincide with the learning objective of FSCIL and the local pseudo incremental tasks are designed to improve the model's plasticity, respectively. Furthermore, to make convincing incremental predictions, we introduce a complementary model with a squared Euclidean-distance classifier as the auxiliary module, which couples with the widely used cosine classifier to form our whole architecture. By such a way, equipped with model decoupling strategy, we can maintain the model's stability while enhancing the model's plasticity. Extensive quantitative and qualitative experiments on three popular FSCIL benchmark datasets demonstrate that our proposed method, named Knowledge Transfer-driven Relation Complementation Network (KT-RCNet), outperforms almost all prior methods. More precisely, the average accuracy of our proposed KT-RCNet outperforms the second-best method by a margin of 5.26%, 3.49%, and 2.25% on miniImageNet, CIFAR100, and CUB200, respectively. Our code is available at https://github.com/YeZiLaiXi/KT-RCNet.git.
Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance. To make MVL methods more practical in an open-ended environment, this paper investigates a novel paradigm called multi-view class incremental learning (MVCIL), where a single model incrementally classifies new classes from a continual stream of views, requiring no access to earlier views of data. However, MVCIL is challenged by the catastrophic forgetting of old information and the interference with learning new concepts. To address this, we first develop a randomization-based representation learning technique serving for feature extraction to guarantee their separate view-optimal working states, during which multiple views belonging to a class are presented sequentially; Then, we integrate them one by one in the orthogonality fusion subspace spanned by the extracted features; Finally, we introduce selective weight consolidation for learning-without-forgetting decision-making while encountering new classes. Extensive experiments on synthetic and real-world datasets validate the effectiveness of our approach.
Pre-trained deep neural networks (DNNs) are being widely deployed by industry for making business decisions and to serve users; however, a major problem is model decay, where the DNN's predictions become more erroneous over time, resulting in revenue loss or unhappy users. To mitigate model decay, DNNs are retrained from scratch using old and new data. This is computationally expensive, so retraining happens only once performance significantly decreases. Here, we study how continual learning (CL) could potentially overcome model decay in large pre-trained DNNs and greatly reduce computational costs for keeping DNNs up-to-date. We identify the "stability gap" as a major obstacle in our setting. The stability gap refers to a phenomenon where learning new data causes large drops in performance for past tasks before CL mitigation methods eventually compensate for this drop. We test two hypotheses to investigate the factors influencing the stability gap and identify a method that vastly reduces this gap. In large-scale experiments for both easy and hard CL distributions (e.g., class incremental learning), we demonstrate that our method reduces the stability gap and greatly increases computational efficiency. Our work aligns CL with the goals of the production setting, where CL is needed for many applications.
Deep neural networks (DNNs) struggle to learn in dynamic environments since they rely on fixed datasets or stationary environments. Continual learning (CL) aims to address this limitation and enable DNNs to accumulate knowledge incrementally, similar to human learning. Inspired by how our brain consolidates memories, a powerful strategy in CL is replay, which involves training the DNN on a mixture of new and all seen classes. However, existing replay methods overlook two crucial aspects of biological replay: 1) the brain replays processed neural patterns instead of raw input, and 2) it prioritizes the replay of recently learned information rather than revisiting all past experiences. To address these differences, we propose SHARP, an efficient neuro-inspired CL method that leverages sparse dynamic connectivity and activation replay. Unlike other activation replay methods, which assume layers not subjected to replay have been pretrained and fixed, SHARP can continually update all layers. Also, SHARP is unique in that it only needs to replay few recently seen classes instead of all past classes. Our experiments on five datasets demonstrate that SHARP outperforms state-of-the-art replay methods in class incremental learning. Furthermore, we showcase SHARP's flexibility in a novel CL scenario where the boundaries between learning episodes are blurry. The SHARP code is available at \url{https://github.com/BurakGurbuz97/SHARP-Continual-Learning}.
Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former ones. While traditional CIL methods focus on visual information to grasp core features, recent advances in Vision-Language Models (VLM) have shown promising capabilities in learning generalizable representations with the aid of textual information. However, when continually trained with new classes, VLMs often suffer from catastrophic forgetting of former knowledge. Applying VLMs to CIL poses two major challenges: 1) how to adapt the model without forgetting; and 2) how to make full use of the multi-modal information. To this end, we propose PROjectiOn Fusion (PROOF) that enables VLMs to learn without forgetting. To handle the first challenge, we propose training task-specific projections based on the frozen image/text encoders. When facing new tasks, new projections are expanded and former projections are fixed, alleviating the forgetting of old concepts. For the second challenge, we propose the fusion module to better utilize the cross-modality information. By jointly adjusting visual and textual features, the model can capture semantic information with stronger representation ability. Extensive experiments on nine benchmark datasets validate PROOF achieves state-of-the-art performance.
Class-incremental learning (CIL) is a particularly challenging variant of continual learning, where the goal is to learn to discriminate between all classes presented in an incremental fashion. Existing approaches often suffer from excessive forgetting and imbalance of the scores assigned to classes that have not been seen together during training. In this study, we introduce a novel approach, Prediction Error-based Classification (PEC), which differs from traditional discriminative and generative classification paradigms. PEC computes a class score by measuring the prediction error of a model trained to replicate the outputs of a frozen random neural network on data from that class. The method can be interpreted as approximating a classification rule based on Gaussian Process posterior variance. PEC offers several practical advantages, including sample efficiency, ease of tuning, and effectiveness even when data are presented one class at a time. Our empirical results show that PEC performs strongly in single-pass-through-data CIL, outperforming other rehearsal-free baselines in all cases and rehearsal-based methods with moderate replay buffer size in most cases across multiple benchmarks.
Class-incremental learning is one of the most important settings for the study of Continual Learning, as it closely resembles real-world application scenarios. With constrained memory sizes, catastrophic forgetting arises as the number of classes/tasks increases. Studying continual learning in the video domain poses even more challenges, as video data contains a large number of frames, which places a higher burden on the replay memory. The current common practice is to sub-sample frames from the video stream and store them in the replay memory. In this paper, we propose SMILE a novel replay mechanism for effective video continual learning based on individual/single frames. Through extensive experimentation, we show that under extreme memory constraints, video diversity plays a more significant role than temporal information. Therefore, our method focuses on learning from a small number of frames that represent a large number of unique videos. On three representative video datasets, Kinetics, UCF101, and ActivityNet, the proposed method achieves state-of-the-art performance, outperforming the previous state-of-the-art by up to 21.49%.
Few-shot class-incremental learning (FSCIL) presents the primary challenge of balancing underfitting to a new session's task and forgetting the tasks from previous sessions. To address this challenge, we develop a simple yet powerful learning scheme that integrates effective methods for each core component of the FSCIL network, including the feature extractor, base session classifiers, and incremental session classifiers. In feature extractor training, our goal is to obtain balanced generic representations that benefit both current viewable and unseen or past classes. To achieve this, we propose a balanced supervised contrastive loss that effectively balances these two objectives. In terms of classifiers, we analyze and emphasize the importance of unifying initialization methods for both the base and incremental session classifiers. Our method demonstrates outstanding ability for new task learning and preventing forgetting on CUB200, CIFAR100, and miniImagenet datasets, with significant improvements over previous state-of-the-art methods across diverse metrics. We conduct experiments to analyze the significance and rationale behind our approach and visualize the effectiveness of our representations on new tasks. Furthermore, we conduct diverse ablation studies to analyze the effects of each module.
Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be constantly updated to incorporate new classes, and the drift in decision boundary may lead to severe forgetting. This fundamental challenge, however, has not yet been studied extensively, especially in the setting where no samples from old classes are stored for rehearsal. In this paper, we take a closer look at how the drift in the classifier leads to forgetting, and accordingly, design four simple yet (super-) effective solutions to alleviate the classifier drift: an Individual Classifiers with Frozen Feature Extractor (ICE) framework where we individually train a classifier for each learning session, and its three variants ICE-PL, ICE-O, and ICE-PL&O which further take the logits of previously learned classes from old sessions or a constant logit of an Other class as a constraint to the learning of new classifiers. Extensive experiments and analysis on 6 class-incremental information extraction tasks demonstrate that our solutions, especially ICE-O, consistently show significant improvement over the previous state-of-the-art approaches with up to 44.7% absolute F-score gain, providing a strong baseline and insights for future research on class-incremental learning.
Incremental learning (IL) suffers from catastrophic forgetting of old tasks when learning new tasks. This can be addressed by replaying previous tasks' data stored in a memory, which however is usually prone to size limits and privacy leakage. Recent studies store only class centroids as prototypes and augment them with Gaussian noises to create synthetic data for replay. However, they cannot effectively avoid class interference near their margins that leads to forgetting. Moreover, the injected noises distort the rich structure between real data and prototypes, hence even detrimental to IL. In this paper, we propose YONO that You Only Need to replay One condensed prototype per class, which for the first time can even outperform memory-costly exemplar-replay methods. To this end, we develop a novel prototype learning method that (1) searches for more representative prototypes in high-density regions by an attentional mean-shift algorithm and (2) moves samples in each class to their prototype to form a compact cluster distant from other classes. Thereby, the class margins are maximized, which effectively reduces interference causing future forgetting. In addition, we extend YONO to YONO+, which creates synthetic replay data by random sampling in the neighborhood of each prototype in the representation space. We show that the synthetic data can further improve YONO. Extensive experiments on IL benchmarks demonstrate the advantages of YONO/YONO+ over existing IL methods in terms of both accuracy and forgetting.
Existing continual learning (CL) research regards catastrophic forgetting (CF) as almost the only challenge. This paper argues for another challenge in class-incremental learning (CIL), which we call cross-task class discrimination (CTCD),~i.e., how to establish decision boundaries between the classes of the new task and old tasks with no (or limited) access to the old task data. CTCD is implicitly and partially dealt with by replay-based methods. A replay method saves a small amount of data (replay data) from previous tasks. When a batch of current task data arrives, the system jointly trains the new data and some sampled replay data. The replay data enables the system to partially learn the decision boundaries between the new classes and the old classes as the amount of the saved data is small. However, this paper argues that the replay approach also has a dynamic training bias issue which reduces the effectiveness of the replay data in solving the CTCD problem. A novel optimization objective with a gradient-based adaptive method is proposed to dynamically deal with the problem in the online CL process. Experimental results show that the new method achieves much better results in online CL.
Human intelligence gradually accepts new information and accumulates knowledge throughout the lifespan. However, deep learning models suffer from a catastrophic forgetting phenomenon, where they forget previous knowledge when acquiring new information. Class-Incremental Learning aims to create an integrated model that balances plasticity and stability to overcome this challenge. In this paper, we propose a selective regularization method that accepts new knowledge while maintaining previous knowledge. We first introduce an asymmetric feature distillation method for old and new classes inspired by cognitive science, using the gradient of classification and knowledge distillation losses to determine whether to perform pattern completion or pattern separation. We also propose a method to selectively interpolate the weight of the previous model for a balance between stability and plasticity, and we adjust whether to transfer through model confidence to ensure the performance of the previous class and enable exploratory learning. We validate the effectiveness of the proposed method, which surpasses the performance of existing methods through extensive experimental protocols using CIFAR-100, ImageNet-Subset, and ImageNet-Full.