Learning how to generalize the model to unseen domains is an important area of research. In this paper, we propose TripleE, and the main idea is to encourage the network to focus on training on subsets (learning with replay) and enlarge the data space in learning on subsets. Learning with replay contains two core designs, EReplayB and EReplayD, which conduct the replay schema on batch and dataset, respectively. Through this, the network can focus on learning with subsets instead of visiting the global set at a glance, enlarging the model diversity in ensembling. To enlarge the data space in learning on subsets, we verify that an exhaustive and singular augmentation (ESAug) performs surprisingly well on expanding the data space in subsets during replays. Our model dubbed TripleE is frustratingly easy, based on simple augmentation and ensembling. Without bells and whistles, our TripleE method surpasses prior arts on six domain generalization benchmarks, showing that this approach could serve as a stepping stone for future research in domain generalization.
Artificial learning systems aspire to mimic human intelligence by continually learning from a stream of tasks without forgetting past knowledge. One way to enable such learning is to store past experiences in the form of input examples in episodic memory and replay them when learning new tasks. However, performance of such method suffers as the size of the memory becomes smaller. In this paper, we propose a new approach for experience replay, where we select the past experiences by looking at the saliency maps which provide visual explanations for the model's decision. Guided by these saliency…
In continual learning, the learner faces a stream of data whose distribution changes over time. Modern neural networks are known to suffer under this setting, as they quickly forget previously acquired knowledge. To address such catastrophic forgetting, many continual learning methods implement different types of experience replay, re-learning on past data stored in a small buffer known as episodic memory. In this work, we complement experience replay with a new objective that we call anchoring, where the learner uses bilevel optimization to update its knowledge on the current task, while keep…
In continual learning, model needs to continually learn a feature extractor and classifier on a sequence of tasks. This paper focuses on how to learn a classifier based on a pretrained feature extractor under continual learning setting. We present an probabilistic analysis that the failure of vanilla experience replay (ER) comes from unnecessary re-learning of previous tasks and incompetence to distinguish current task from the previous ones, which is the cause of knowledge degradation and prediction bias. To overcome these weaknesses, we propose a novel replay strategy task-aware experience r…
Artificial Intelligence, Analytics And Informatics (AI), A*STAR（A*STAR人工智能、分析与信息学）；RMIT University（皇家墨尔本理工大学）；Institute for Infocomm Research (IR), A*STAR（A*STAR资讯通信研究院）
Deep neural networks have shown promise in several domains, and the learned data (task) specific information is implicitly stored in the network parameters. Extraction and utilization of encoded knowledge representations are vital when data is no longer available in the future, especially in a continual learning scenario. In this work, we introduce {\em flashcards}, which are visual representations that {\em capture} the encoded knowledge of a network as a recursive function of predefined random image patterns. In a continual learning scenario, flashcards help to prevent catastrophic forgettin…
Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful strategies against catastrophic forgetting. However, since forgetting is inevitable given bounded memory and unbounded tasks, how to forget is a problem continual learning must address. Therefore, beyond simply avoiding catastrophic forgetting, an under-explored issue is how to reasonably forget while ensuring the merits of human memory, including 1. storage …
Advanced Research Lab, NavInfo Europe（四维图新欧洲高级研究实验室）
Continual learning (CL) in the brain is facilitated by a complex set of mechanisms. This includes the interplay of multiple memory systems for consolidating information as posited by the complementary learning systems (CLS) theory and synaptic consolidation for protecting the acquired knowledge from erasure. Thus, we propose a general CL method that creates a synergy between SYNaptic consolidation and dual memory Experience Replay (SYNERgy). Our method maintains a semantic memory that accumulates and consolidates information across the tasks and interacts with the episodic memory for effective…
University of Oxford（牛津大学）；Facebook AI Research（脸书人工智能研究院）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Australian National University（澳大利亚国立大学）
University of Amsterdam（阿姆斯特丹大学）；Inception Institute of Artificial Intelligence（Inception人工智能研究院）
This paper introduces kernel continual learning, a simple but effective variant of continual learning that leverages the non-parametric nature of kernel methods to tackle catastrophic forgetting. We deploy an episodic memory unit that stores a subset of samples for each task to learn task-specific classifiers based on kernel ridge regression. This does not require memory replay and systematically avoids task interference in the classifiers. We further introduce variational random features to learn a data-driven kernel for each task. To do so, we formulate kernel continual learning as a variati…
FETCH: A Memory-Efficient Replay Approach for Continual Learning in Image Classification
Faculty of Electrical Engineering and Information Technology, Chemnitz University of Technology（德国 Chemnitz 工业大学 电气工程与信息技术学院）；Institute for Computational Visualistics, University of Koblenz（科布伦茨大学 计算视觉学研究所）
Advanced Research Lab, NavInfo Europe（四维图新欧洲高级研究实验室）；Eindhoven University of Technology（埃因霍温理工大学）
Humans excel at lifelong learning, as the brain has evolved to be robust to distribution shifts and noise in our ever-changing environment. Deep neural networks (DNNs), however, exhibit catastrophic forgetting and the learned representations drift drastically as they encounter a new task. This alludes to a different error-based learning mechanism in the brain. Unlike DNNs, where learning scales linearly with the magnitude of the error, the sensitivity to errors in the brain decreases as a function of their magnitude. To this end, we propose \textit{ESMER} which employs a principled mechanism t…
Humans excel at continually learning from an ever-changing environment whereas it remains a challenge for deep neural networks which exhibit catastrophic forgetting. The complementary learning system (CLS) theory suggests that the interplay between rapid instance-based learning and slow structured learning in the brain is crucial for accumulating and retaining knowledge. Here, we propose CLS-ER, a novel dual memory experience replay (ER) method which maintains short-term and long-term semantic memories that interact with the episodic memory. Our method employs an effective replay mechanism whe…
Online continual learning in the wild is a very difficult task in machine learning. Non-stationarity in online continual learning potentially brings about catastrophic forgetting in neural networks. Specifically, online continual learning for autonomous driving with SODA10M dataset exhibits extra problems on extremely long-tailed distribution with continuous distribution shift. To address these problems, we propose multiple deep metric representation learning via both contrastive and supervised contrastive learning alongside soft labels distillation to improve model generalization. Moreover, w…
University of Oxford（牛津大学）；Five AI Ltd（Five AI有限公司）
In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experience is finished. The prior art in CL uses episodic memory, parameter regularization or extensible network structures to reduce interference among tasks, but in the end, all the approaches learn different tasks in a joint vector space. We believe this invariably leads to interference among different tasks. We propose to learn tasks in different (low-rank) vector subspaces that are kept orthogonal to each other in orde…
Humans learn to recognize and manipulate new objects in lifelong settings without forgetting the previously gained knowledge under non-stationary and sequential conditions. In autonomous systems, the agents also need to mitigate similar behavior to continually learn the new object categories and adapt to new environments. In most conventional deep neural networks, this is not possible due to the problem of catastrophic forgetting, where the newly gained knowledge overwrites existing representations. Furthermore, most state-of-the-art models excel either in recognizing the objects or in grasp p…
The core challenge with continual learning is catastrophic forgetting, the phenomenon that when neural networks are trained on a sequence of tasks they rapidly forget previously learned tasks. It has been observed that catastrophic forgetting is most severe when tasks are dissimilar to each other. We propose the use of sparse routing networks for continual learning. For each input, these network architectures activate a different path through a network of experts. Routing networks have been shown to learn to route similar tasks to overlapping sets of experts and dissimilar tasks to disjoint se…
SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators
Department of Mechanical Engineering, University of Utah, Salt Lake City, UT, USA（犹他大学机械工程系）；Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT, USA（犹他大学科学计算与成像研究所）；Department of Mechanical Engineering, University of Wisconsin–Milwaukee, Milwaukee, WI, USA（威斯康星大学密尔沃基分校机械工程系）；Department of Biomedical Engineering, University of Utah, Salt Lake City, UT, USA（犹他大学生物医学工程系）
China University of Petroleum Beijing (CUP)（中国石油大学（北京））
Continual learning aims to rapidly and continually learn the current task from a sequence of tasks. Compared to other kinds of methods, the methods based on experience replay have shown great advantages to overcome catastrophic forgetting. One common limitation of this method is the data imbalance between the previous and current tasks, which would further aggravate forgetting. Moreover, how to effectively address the stability-plasticity dilemma in this setting is also an urgent problem to be solved. In this paper, we overcome these challenges by proposing a novel framework called Meta-learni…
Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；School of Public Health, Peking University（北京大学公共卫生学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Peng Cheng Laboratory（鹏城实验室）
