Prototype Reminding for Continual Learning

By Mengmi Zhang, Tao Wang, Joo Hwee Lim, Jiashi Feng. 2019

13 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Meta & Continual Learning

Citations in the corpus

Kernel Continual Learning (2021, background): “, 2019) assume it is possible to access data from previous tasks by having a fixedsize memory or a generative model able to produce samples from old tasks (Lopez-Paz & Ranzato, 2017; Riemer et al., 2019; Rios & Itti, 2018; Shin et al., 2017; Zhang et al., 2019).”
Efficient Continual Learning with Modular Networks and Task-Driven Priors (2020, background): “For instance, Lopez-Paz & Ranzato (2017); Chaudhry et al. (2019b); Rolnick et al. (2019) store past samples in a replay buffer, while Shin et al. (2017) learn to generate new samples from the data distribution of previous tasks and Zhang et al. (2019) computes per-class prototypes.”
Linear Mode Connectivity in Multitask and Continual Learning (2020, background): “Experience replay: Experience replay methods build and store a memory of the knowledge learned so far (Rebuffi et al., 2016; Lopez-Paz & Ranzato, 2017; Shin et al., 2017; Riemer et al., 2018; Rios & Itti, 2018; Zhang et al., 2019).”
Understanding the Role of Training Regimes in Continual Learning (2020, background): “The ﬁrst group consists of replay based methods that build and store a memory of the knowledge learned from old tasks [46, 59, 78, 65, 60], known as experience replay . iCaRL [58] learns in a class-incremental way by having a ﬁxed memory that stores samples that are close to the center of each…”
Adversarial Continual Learning (2020, methodology): “We use common image classification datasets including 5-Split MNIST and Permuted MNIST [20], previously used in [25,42,10], 20-Split CIFAR100 [19] used in [42,21,6], and 20-Split miniImageNet [38] used in [7,43].”
Orthogonal Gradient Descent for Continual Learning (2019, background): “Shin et al. (2017); Kamra et al. (2017); Zhang et al. (2019); Rios and Itti (2018) learned a generative model to capture the data distribution of previous tasks, along with the current task’s data to train the new model so that the forgetting can be alleviated.”
Task-agnostic Continual Learning with Hybrid Probabilistic Models (2021, unknown): “Replay - based methods store and rephrase a memory of the examples or knowledge learned so far [Rebuﬃ et al., 2016, Lopez-Paz and Ranzato, 2017, Shin et al., 2017, Riemer et al., 2018, Rios and Itti, 2018, Zhang et al., 2019, Chaudhry et al., 2020, Balaji et al., 2020].”
Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint. (2020, methodology): “The replay-based methods store previous data or, alternatively, train a generative model of them and replay samples from them interleaved with samples drawn from the current task (Shin et al., 2017; Kamra et al., 2017; Zhang et al., 2019; Rios and Itti, 2018; Lüders et al., 2016; Lopez-Paz and Ranza”