If α > β, we are overemphasizing the contribution of the first term of Eq. 9 (which brings each layer'sλk1 andck close toeach other) overthesecond one(which induces small Lipschitz targets).

We thank the reviewers for the constructive feedback. Code will be made public. Fig. (a, b, c) best viewed in zoom. See R3.1 for comparison between random selection and genetic algorithms. Our proposed RPS-Net consistently performs better across all budgets.

Class-incremental continual learning into the extended der-verse.

The dynamic environment of laboratories and clinics, with streams of data arriving on a daily basis, requires regular updates of trained machine learning models for consistent performance. Continual learning is supposed to help train models without catastrophic forgetting. However, state-of-the-art methods are ineffective for multiple instance learning (MIL), which is often used in single-cell-based hematologic disease diagnosis (e.g., leukemia detection). Here, we propose the first continual learning method tailored specifically to MIL. Our method is rehearsal-based over a selection of single instances from various bags. We use a combination of the instance attention score and distance from the bag mean and class mean vectors to carefully select which samples and instances to store in exemplary sets from previous tasks, preserving the diversity of the data. Using the real-world input of one month of data from a leukemia laboratory, we study the effectiveness of our approach in a class incremental scenario, comparing it to well-known continual learning methods. We show that our method considerably outperforms state-of-the-art methods, providing the first continual learning approach for MIL. This enables the adaptation of models to shifting data distributions over time, such as those caused by changes in disease occurrence or underlying genetic alterations.

Summary and Contributions: Update: My initial review noted two main issues with the paper: reliance on the initial model, and the use of task labels during the test phase. The author response addresses the first question, but misses the point on the second one. And this alone is not sufficient to strongly influence my overall rating. In my understanding, several previous methods, such as LwF, iCaRL highlighted in the author response, classify samples without the knowledge of which group of classes (i.e., old or new) they belong to. In other words, they only use a single framework that can identify samples from any of the old or the new classes, without additional information.

The authors of the manuscript consider the continuum learning setting, where the learner observes a stream of data points from training, which are ordered according to the tasks they belong to, i.e. the learner encounters any data from the next task only after it has observed all the training data for the current one. The authors propose a set of three metrics for evaluation performance of learning algorithms in this setting, which reflect their ability to transfer information to new tasks and not forget information about the earlier tasks. Could the authors, please, comment on the difference between continuum and lifelong learning (the corresponding sentence in line 254 seems incomplete)? The authors also propose a learning method, termed Gradient of Episodic Memory (GEM). The idea of the method is to keep a set of examples from every observed task and make sure that at each update stage the loss on the observed tasks does not increase.

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%.

Catastrophic forgetting in neural networks during incremental learning remains a challenging problem. Previous research investigated catastrophic forgetting in fully connected networks, with some earlier work exploring activation functions and learning algorithms. Applications of neural networks have been extended to include similarity learning. Understanding how similarity learning loss functions would be affected by catastrophic forgetting is of significant interest. Our research investigates catastrophic forgetting for four well-known similarity-based loss functions during incremental class learning. The loss functions are Angular, Contrastive, Center, and Triplet loss. Our results show that the catastrophic forgetting rate differs across loss functions on multiple datasets. The Angular loss was least affected, followed by Contrastive, Triplet loss, and Center loss with good mining techniques. We implemented three existing incremental learning techniques, iCaRL, EWC, and EBLL. We further proposed a novel technique using Variational Autoencoders (VAEs) to generate representation as exemplars passed through the network's intermediate layers. Our method outperformed three existing state-of-the-art techniques. We show that one does not require stored images (exemplars) for incremental learning with similarity learning. The generated representations from VAEs help preserve regions of the embedding space used by prior knowledge so that new knowledge does not ``overwrite'' it.

Intelligent fault diagnosis has made extraordinary advancements currently. Nonetheless, few works tackle class-incremental learning for fault diagnosis under limited fault data, i.e., imbalanced and long-tailed fault diagnosis, which brings about various notable challenges. Initially, it is difficult to extract discriminative features from limited fault data. Moreover, a well-trained model must be retrained from scratch to classify the samples from new classes, thus causing a high computational burden and time consumption. Furthermore, the model may suffer from catastrophic forgetting when trained incrementally. Finally, the model decision is biased toward the new classes due to the class imbalance. The problems can consequently lead to performance degradation of fault diagnosis models. Accordingly, we introduce a supervised contrastive knowledge distillation for incremental fault diagnosis under limited fault data (SCLIFD) framework to address these issues, which extends the classical incremental classifier and representation learning (iCaRL) framework from three perspectives. Primarily, we adopt supervised contrastive knowledge distillation (KD) to enhance its representation learning capability under limited fault data. Moreover, we propose a novel prioritized exemplar selection method adaptive herding (AdaHerding) to restrict the increase of the computational burden, which is also combined with KD to alleviate catastrophic forgetting. Additionally, we adopt the cosine classifier to mitigate the adverse impact of class imbalance. We conduct extensive experiments on simulated and real-world industrial processes under different imbalance ratios. Experimental results show that our SCLIFD outperforms the existing methods by a large margin.