The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical for designing intelligent systems. Many existing approaches to continual learning rely on stochastic gradient descent and its variants. However, these algorithms have to implement various strategies, such as memory buffers or replay, to overcome well-known shortcomings of stochastic gradient descent methods in terms of stability, greed, and short-term memory. To that end, we develop a biologically-inspired light weight neural network architecture that incorporates local learning and neuromodulation to enable input processing over data streams and online learning. Next, we address the challenge of hyperparameter selection for tasks that are not known in advance by implementing transfer metalearning: using a Bayesian optimization to explore a design space spanning multiple local learning rules and their hyperparameters, we identify high performing configurations in classical single task online learning and we transfer them to continual learning tasks with task-similarity considerations. We demonstrate the efficacy of our approach on both single task and continual learning setting. For the single task learning setting, we demonstrate superior performance over other local learning approaches on the MNIST, Fashion MNIST, and CIFAR-10 datasets. Using high performing configurations metalearned in the single task learning setting, we achieve superior continual learning performance on Split-MNIST, and Split-CIFAR-10 data as compared with other memory-constrained learning approaches, and match that of the state-of-the-art memory-intensive replay-based approaches.
The continual learning (CL) paradigm aims to enable neural networks to learn tasks continually in a sequential fashion. The fundamental challenge in this learning paradigm is catastrophic forgetting previously learned tasks when the model is optimized for a new task, especially when their data is not accessible. Current architectural-based methods aim at alleviating the catastrophic forgetting problem but at the expense of expanding the capacity of the model. Regularization-based methods maintain a fixed model capacity; however, previous studies showed the huge performance degradation of these methods when the task identity is not available during inference (e.g. class incremental learning scenario). In this work, we propose a novel architectural-based method referred as SpaceNet for class incremental learning scenario where we utilize the available fixed capacity of the model intelligently. SpaceNet trains sparse deep neural networks from scratch in an adaptive way that compresses the sparse connections of each task in a compact number of neurons. The adaptive training of the sparse connections results in sparse representations that reduce the interference between the tasks. Experimental results show the robustness of our proposed method against catastrophic forgetting old tasks and the efficiency of SpaceNet in utilizing the available capacity of the model, leaving space for more tasks to be learned. In particular, when SpaceNet is tested on the well-known benchmarks for CL: split MNIST, split Fashion-MNIST, and CIFAR-10/100, it outperforms regularization-based methods by a big performance gap. Moreover, it achieves better performance than architectural-based methods without model expansion and achieved comparable results with rehearsal-based methods, while offering a huge memory reduction.
As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and fast adaptation to new knowledge. In this paper, we concentrate on this "slow vs. fast" (SvF) dilemma to determine which knowledge components to be updated in a slow fashion or a fast fashion, and thereby balance old-knowledge preservation and new-knowledge adaptation. We propose a multi-grained SvF learning strategy to cope with the SvF dilemma from two different grains: intra-space (within the same feature space) and inter-space (between two different feature spaces). The proposed strategy designs a novel frequency-aware regularization to boost the intra-space SvF capability, and meanwhile develops a new feature space composition operation to enhance the inter-space SvF learning performance. With the multi-grained SvF learning strategy, our method outperforms the state-of-the-art approaches by a large margin.
Continual learning aims to learn tasks sequentially, with (often severe) constraints on the storage of old learning samples, without suffering from catastrophic forgetting. In this work, we propose prescient continual learning, a novel experimental setting, to incorporate existing information about the classes, prior to any training data. Usually, each task in a traditional continual learning setting evaluates the model on present and past classes, the latter with a limited number of training samples. Our setting adds future classes, with no training samples at all. We introduce Ghost Model, a representation-learning-based model for continual learning using ideas from zero-shot learning. A generative model of the representation space in concert with a careful adjustment of the losses allows us to exploit insights from future classes to constraint the spatial arrangement of the past and current classes. Quantitative results on the AwA2 and aP\&Y datasets and detailed visualizations showcase the interest of this new setting and the method we propose to address it.
Lifelong or continual learning remains to be a challenge for artificial neural network, as it is required to be both stable for preservation of old knowledge and plastic for acquisition of new knowledge. It is common to see previous experience get overwritten, which leads to the well-known issue of catastrophic forgetting, especially in the scenario of class-incremental learning (Class-IL). Recently, many lifelong learning methods have been proposed to avoid catastrophic forgetting. However, models which learn without replay of the input data, would encounter another problem which has been ignored, and we refer to it as prior information loss (PIL). In training procedure of Class-IL, as the model has no knowledge about following tasks, it would only extract features necessary for tasks learned so far, whose information is insufficient for joint classification. In this paper, our empirical results on several image datasets show that PIL limits the performance of current state-of-the-art method for Class-IL, the orthogonal weights modification (OWM) algorithm. Furthermore, we propose to combine self-supervised learning, which can provide effective representations without requiring labels, with Class-IL to partly get around this problem. Experiments show superiority of proposed method to OWM, as well as other strong baselines.
While neural networks trained for semantic segmentation are essential for perception in autonomous driving, most current algorithms assume a fixed number of classes, presenting a major limitation when developing new autonomous driving systems with the need of additional classes. In this paper we present a technique implementing class-incremental learning for semantic segmentation without using the labeled data the model was initially trained on. Previous approaches still either rely on labels for both old and new classes, or fail to properly distinguish between them. We show how to overcome these problems with a novel class-incremental learning technique, which nonetheless requires labels only for the new classes. Specifically, (i) we introduce a new loss function that neither relies on old data nor on old labels, (ii) we show how new classes can be integrated in a modular fashion into pretrained semantic segmentation models, and finally (iii) we re-implement previous approaches in a unified setting to compare them to ours. We evaluate our method on the Cityscapes dataset, where we exceed the mIoU performance of all baselines by 3.5% absolute reaching a result, which is only 2.2% absolute below the upper performance limit of single-stage training, relying on all data and labels simultaneously.
The ability of intelligent agents to learn and remember multiple tasks sequentially is crucial to achieving artificial general intelligence. Many continual learning (CL) methods have been proposed to overcome catastrophic forgetting which results from non i.i.d data in the sequential learning of neural networks. In this paper we focus on class incremental learning, a challenging CL scenario. For this scenario, generative replay is a promising strategy which generates and replays pseudo data for previous tasks to alleviate catastrophic forgetting. However, it is hard to train a generative model continually for relatively complex data. Based on recently proposed orthogonal weight modification (OWM) algorithm which can approximately keep previously learned feature invariant when learning new tasks, we propose to 1) replay penultimate layer feature with a generative model; 2) leverage a self-supervised auxiliary task to further enhance the stability of feature. Empirical results on several datasets show our method always achieves substantial improvement over powerful OWM while conventional generative replay always results in a negative effect. Meanwhile our method beats several strong baselines including one based on real data storage. In addition, we conduct experiments to study why our method is effective.
Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learning. In this work, we propose PODNet, a model inspired by representation learning. By carefully balancing the compromise between remembering the old classes and learning new ones, PODNet fights catastrophic forgetting, even over very long runs of small incremental tasks --a setting so far unexplored by current works. PODNet innovates on existing art with an efficient spatial-based distillation-loss applied throughout the model and a representation comprising multiple proxy vectors for each class. We validate those innovations thoroughly, comparing PODNet with three state-of-the-art models on three datasets: CIFAR100, ImageNet100, and ImageNet1000. Our results showcase a significant advantage of PODNet over existing art, with accuracy gains of 12.10, 6.51, and 2.85 percentage points, respectively. Code is available at https://github.com/arthurdouillard/incremental_learning.pytorch
Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models. Modern batch contrastive approaches subsume or significantly outperform traditional contrastive losses such as triplet, max-margin and the N-pairs loss. In this work, we extend the self-supervised batch contrastive approach to the fully-supervised setting, allowing us to effectively leverage label information. Clusters of points belonging to the same class are pulled together in embedding space, while simultaneously pushing apart clusters of samples from different classes. We analyze two possible versions of the supervised contrastive (SupCon) loss, identifying the best-performing formulation of the loss. On ResNet-200, we achieve top-1 accuracy of 81.4% on the ImageNet dataset, which is 0.8% above the best number reported for this architecture. We show consistent outperformance over cross-entropy on other datasets and two ResNet variants. The loss shows benefits for robustness to natural corruptions and is more stable to hyperparameter settings such as optimizers and data augmentations. Our loss function is simple to implement, and reference TensorFlow code is released at https://t.ly/supcon.
The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones. To address this problem, we represent the knowledge using a neural gas (NG) network, which can learn and preserve the topology of the feature manifold formed by different classes. On this basis, we propose the TOpology-Preserving knowledge InCrementer (TOPIC) framework. TOPIC mitigates the forgetting of the old classes by stabilizing NG's topology and improves the representation learning for few-shot new classes by growing and adapting NG to new training samples. Comprehensive experimental results demonstrate that our proposed method significantly outperforms other state-of-the-art class-incremental learning methods on CIFAR100, miniImageNet, and CUB200 datasets.
Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the task-ID is unknown at inference time. The imbalance between old and new classes typically results in a bias of the network towards the newest ones. This imbalance problem can either be addressed by storing exemplars from previous tasks, or by using image replay methods. However, the latter can only be applied to toy datasets since image generation for complex datasets is a hard problem. We propose a solution to the imbalance problem based on generative feature replay which does not require any exemplars. To do this, we split the network into two parts: a feature extractor and a classifier. To prevent forgetting, we combine generative feature replay in the classifier with feature distillation in the feature extractor. Through feature generation, our method reduces the complexity of generative replay and prevents the imbalance problem. Our approach is computationally efficient and scalable to large datasets. Experiments confirm that our approach achieves state-of-the-art results on CIFAR-100 and ImageNet, while requiring only a fraction of the storage needed for exemplar-based continual learning. Code available at \url{https://github.com/xialeiliu/GFR-IL}.
Continual Learning has inspired a plethora of approaches and evaluation settings; however, the majority of them overlooks the properties of a practical scenario, where the data stream cannot be shaped as a sequence of tasks and offline training is not viable. We work towards General Continual Learning (GCL), where task boundaries blur and the domain and class distributions shift either gradually or suddenly. We address it through mixing rehearsal with knowledge distillation and regularization; our simple baseline, Dark Experience Replay, matches the network's logits sampled throughout the optimization trajectory, thus promoting consistency with its past. By conducting an extensive analysis on both standard benchmarks and a novel GCL evaluation setting (MNIST-360), we show that such a seemingly simple baseline outperforms consolidated approaches and leverages limited resources. We further explore the generalization capabilities of our objective, showing its regularization being beneficial beyond mere performance.
Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this setting, networks suffer from catastrophic forgetting which refers to the drastic drop in performance on previous tasks. The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes. Embedding networks have the advantage that new classes can be naturally included into the network without adding new weights. Therefore, we study incremental learning for embedding networks. In addition, we propose a new method to estimate the drift, called semantic drift, of features and compensate for it without the need of any exemplars. We approximate the drift of previous tasks based on the drift that is experienced by current task data. We perform experiments on fine-grained datasets, CIFAR100 and ImageNet-Subset. We demonstrate that embedding networks suffer significantly less from catastrophic forgetting. We outperform existing methods which do not require exemplars and obtain competitive results compared to methods which store exemplars. Furthermore, we show that our proposed SDC when combined with existing methods to prevent forgetting consistently improves results.
We consider class incremental learning (CIL) problem, in which a learning agent continuously learns new classes from incrementally arriving training data batches and aims to predict well on all the classes learned so far. The main challenge of the problem is the catastrophic forgetting, and for the exemplar-memory based CIL methods, it is generally known that the forgetting is commonly caused by the classification score bias that is injected due to the data imbalance between the new classes and the old classes (in the exemplar-memory). While several methods have been proposed to correct such score bias by some additional post-processing, e.g., score re-scaling or balanced fine-tuning, no systematic analysis on the root cause of such bias has been done. To that end, we analyze that computing the softmax probabilities by combining the output scores for all old and new classes could be the main cause of the bias. Then, we propose a new method, dubbed as Separated Softmax for Incremental Learning (SS-IL), that consists of separated softmax (SS) output layer combined with task-wise knowledge distillation (TKD) to resolve such bias. Throughout our extensive experimental results on several large-scale CIL benchmark datasets, we show our SS-IL achieves strong state-of-the-art accuracy through attaining much more balanced prediction scores across old and new classes, without any additional post-processing.
Continual acquisition of novel experience without interfering previously learned knowledge, i.e. continual learning, is critical for artificial neural networks, but limited by catastrophic forgetting. A neural network adjusts its parameters when learning a new task, but then fails to conduct the old tasks well. By contrast, the brain has a powerful ability to continually learn new experience without catastrophic interference. The underlying neural mechanisms possibly attribute to the interplay of hippocampus-dependent memory system and neocortex-dependent memory system, mediated by prefrontal cortex. Specifically, the two memory systems develop specialized mechanisms to consolidate information as more specific forms and more generalized forms, respectively, and complement the two forms of information in the interplay. Inspired by such brain strategy, we propose a novel approach named triple memory networks (TMNs) for continual learning. TMNs model the interplay of hippocampus, prefrontal cortex and sensory cortex (a neocortex region) as a triple-network architecture of generative adversarial networks (GAN). The input information is encoded as specific representation of the data distributions in a generator, or generalized knowledge of solving tasks in a discriminator and a classifier, with implementing appropriate brain-inspired algorithms to alleviate catastrophic forgetting in each module. Particularly, the generator replays generated data of the learned tasks to the discriminator and the classifier, both of which are implemented with a weight consolidation regularizer to complement the lost information in generation process. TMNs achieve new state-of-the-art performance on a variety of class-incremental learning benchmarks on MNIST, SVHN, CIFAR-10 and ImageNet-50, comparing with strong baseline methods.
Incremental learning attempts to develop a classifier which learns continuously from a stream of data segregated into different classes. Deep learning approaches suffer from catastrophic forgetting when learning classes incrementally, while most incremental learning approaches require a large amount of training data per class. We examine the problem of incremental learning using only a few training examples, referred to as Few-Shot Incremental Learning (FSIL). To solve this problem, we propose a novel approach inspired by the concept learning model of the hippocampus and the neocortex that represents each image class as centroids and does not suffer from catastrophic forgetting. We evaluate our approach on three class-incremental learning benchmarks: Caltech-101, CUBS-200-2011 and CIFAR-100 for incremental and few-shot incremental learning and show that our approach achieves state-of-the-art results in terms of classification accuracy over all learned classes.
Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting of previous ones. To alleviate this issue, it has been proposed to keep around a few examples of the previous concepts but the effectiveness of this approach heavily depends on the representativeness of these examples. This paper proposes a novel and automatic framework we call mnemonics, where we parameterize exemplars and make them optimizable in an end-to-end manner. We train the framework through bilevel optimizations, i.e., model-level and exemplar-level. We conduct extensive experiments on three MCIL benchmarks, CIFAR-100, ImageNet-Subset and ImageNet, and show that using mnemonics exemplars can surpass the state-of-the-art by a large margin. Interestingly and quite intriguingly, the mnemonics exemplars tend to be on the boundaries between different classes.
Although deep learning performs really well in a wide variety of tasks, it still suffers from catastrophic forgetting -- the tendency of neural networks to forget previously learned information upon learning new tasks where previous data is not available. Earlier methods of incremental learning tackle this problem by either using a part of the old dataset, by generating exemplars or by using memory networks. Although, these methods have shown good results but using exemplars or generating them, increases memory and computation requirements. To solve these problems we propose an adversarial discriminator based method that does not make use of old data at all while training on new tasks. We particularly tackle the class incremental learning problem in image classification, where data is provided in a class-based sequential manner. For this problem, the network is trained using an adversarial loss along with the traditional cross-entropy loss. The cross-entropy loss helps the network progressively learn new classes while the adversarial loss helps in preserving information about the existing classes. Using this approach, we are able to outperform other state-of-the-art methods on CIFAR-100, SVHN, and MNIST datasets.
Incremental learning is useful if an AI agent needs to integrate data from a stream. The problem is non trivial if the agent runs on a limited computational budget and has a bounded memory of past data. In a deep learning approach, the constant computational budget requires the use of a fixed architecture for all incremental states. The bounded memory generates data imbalance in favor of new classes and a prediction bias toward them appears. This bias is commonly countered by introducing a data balancing step in addition to the basic network training. We depart from this approach and propose simple but efficient scaling of past class classifier weights to make them more comparable to those of new classes. Scaling exploits incremental state level statistics and is applied to the classifiers learned in the initial state of classes in order to profit from all their available data. We also question the utility of the widely used distillation loss component of incremental learning algorithms by comparing it to vanilla fine tuning in presence of a bounded memory. Evaluation is done against competitive baselines using four public datasets. Results show that the classifier weights scaling and the removal of the distillation are both beneficial.
Deep neural networks (DNNs) have been applied in class incremental learning, which aims to solve common real-world problems of learning new classes continually. One drawback of standard DNNs is that they are prone to catastrophic forgetting. Knowledge distillation (KD) is a commonly used technique to alleviate this problem. In this paper, we demonstrate it can indeed help the model to output more discriminative results within old classes. However, it cannot alleviate the problem that the model tends to classify objects into new classes, causing the positive effect of KD to be hidden and limited. We observed that an important factor causing catastrophic forgetting is that the weights in the last fully connected (FC) layer are highly biased in class incremental learning. In this paper, we propose a simple and effective solution motivated by the aforementioned observations to address catastrophic forgetting. Firstly, we utilize KD to maintain the discrimination within old classes. Then, to further maintain the fairness between old classes and new classes, we propose Weight Aligning (WA) that corrects the biased weights in the FC layer after normal training process. Unlike previous work, WA does not require any extra parameters or a validation set in advance, as it utilizes the information provided by the biased weights themselves. The proposed method is evaluated on ImageNet-1000, ImageNet-100, and CIFAR-100 under various settings. Experimental results show that the proposed method can effectively alleviate catastrophic forgetting and significantly outperform state-of-the-art methods.