Incremental Learning with Maximum Entropy Regularization: Rethinking Forgetting and Intransigence

By Jihwan Bae, Yeonsik Jo, Jonghyun Choi. 2019

23 citations recorded by the source corpus.

Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the uncertainty accumulates through the tasks by knowledge transfer. To prevent overfitting to the uncertain knowledge, we propose to penalize confident fitting to the uncertain knowledge by the Maximum Entropy Regularizer (MER). Additionally, to reduce class imbalance and induce a self-paced curriculum on new classes, we exclude a few samples from the new classes in every mini-batch, which we call DropOut Sampling (DOS). We further rethink evaluation metrics for forgetting and intransigence in incremental learning by tracking each sample's confusion at the transition of a task since the existing metrics that compute the difference in accuracy are often misleading. We show that the proposed method, named 'MEDIC', outperforms the state-of-the-art incremental learning algorithms in accuracy, forgetting, and intransigence measured by both the existing and the proposed metrics by a large margin in extensive empirical validations on CIFAR100 and a popular subset of ImageNet dataset (TinyImageNet).

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Optimization & Training, 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 Optimization & Training

In Meta & Continual Learning

Citations in the corpus

Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (2021, background): “…of the samples from the previous tasks in an episodic memory (Rebufﬁ et al., 2017; Castro et al., 2018; Chaudhry et al., 2019; Wu et al., 2019; Kim et al., 2019) or keep a generative model that is trained to generate previous task samples (Shin et al., 2017; Wu et al., 2018; Hu et al., 2019;…”
PLOP: Learning without Forgetting for Continual Semantic Segmentation (2020, background): “It has already been shown in related contexts [36] that class ordering can have a large impact on performance.”
ScaIL: Classifier Weights Scaling for Class Incremental Learning (2020, methodology): “Unlike existing IL algorithms which use distillation [5, 7, 10, 12, 22, 34], only classification loss is used.”
A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020, background): “In spite of this observation, knowledge distillation is commonly used to tackle catastrophic forgetting [10, 16, 20, 23, 35, 41, 65].”
Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation (2021, background): “It has already been shown in related contexts [113] that class ordering can have a large impact on performance.”