More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning

By Yu Liu, Sarah Parisot, G. Slabaugh, Xu Jia, Ales Leonardis, Tinne Tuytelaars. 2020

115 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Meta & Continual Learning

Citations in the corpus

Learnability and Algorithm for Continual Learning (2023, methodology): “The average forgetting rate after task t is Ft = ∑t−1 i=1 A i i − Ati (Liu et al., 2020b).”
FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning (2022, methodology): “Auxiliary classiﬁers were introduced in [20] to reduce the effect of forgetting.”
A Theoretical Study on Solving Continual Learning (2022, methodology): “MUC [25] and PASS [26] are regularization-based methods.”
Balancing Stability and Plasticity through Advanced Null Space in Continual Learning (2022, methodology): “…against competitive and well-established methods 4 , including 5 regularization-based methods using importance measure (EWC [17], MAS [1], MUC-MAS [25], SI [58], and CPR [5]), 2 regularization-based methods using knowledge distillation (LwF [23] and GD-WILD [20]), 1 architecture-based method…”
CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One (2022, neutral): “Besides, [22] achieved more effective weight regularization by ensemble of multiple auxiliary classifiers learned from extra out-of-distribution data (e.g., SVHN [33] for CIFAR-100 [21]).”
Representation Compensation Networks for Continual Semantic Segmentation (2022, methodology): “Some methods [43,48,56,66,67,80,95] play regularization on model parameters to improve its stability.”
Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connector (2021, neutral): “We compare our method with EWC [21], MAS [2] , MUC-MAS [26], SI [44], LwF [25], InstAParam [5], GD-WILD [23], GEM [27], A-GEM [4], MEGA [16], OWM [43] and Adam-NSCL [37].”
Training Networks in Null Space of Feature Covariance for Continual Learning (2021, methodology): “We compare our method with various continual learning methods including EWC [22], MAS [3], MUC-MAS [29], SI [38], LwF [27], GD-WILD [24], GEM , [31], A-GEM [7], MEGA [13], InstAParam [8] and OWM [54].”
GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning (2021, background): “…the latter retrain part of it; (iii) Rehearsal based aims at preventing catastrophic forgetting by storing and replaying information from previous episodes (Rebuffi et al., 2017; Castro et al., 2018; Wu et al., 2018; Hou et al., 2019; Zhai et al., 2019; Liu et al., 2020b; jun Liu et al., 2020).”
Balancing Between Forgetting and Acquisition in Incremental Subpopulation Learning (2022, methodology): “Methods like MUC and PASS were tested in CIL, but as stated in their papers [17,42], they are also general for different IL settings including ISL.”
Memory-Free Generative Replay For Class-Incremental Learning (2021, methodology): “The very recent MUC [23] method leverages an auxiliary classifier that is trained on an external dataset and use it to regularize new task model via multiple distillation loss.”
Divide and not forget: Ensemble of selectively trained experts in Continual Learning (2024, methodology): “…amount of data (i.e., 50% of all available classes) (Hou et al., 2019; Zhu et al., 2022; Petit et al., 2023), or it starts from a large pre-trained model that remains unchanged (Hayes & Kanan, 2020a; Wang et al., 2022c) that eliminates the problem of representational drift (Yu et al., 2020).”
Residual Tuning: Toward Novel Category Discovery Without Labels (2022, unknown): “Due to its potential usefulness and effectiveness, continual learning has attracted increasing interests in recent years for a wide range of vision applications, such as image classification [38]–[40], object detection [41], [42], and semantic”