A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks
The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural networks to underfit past data when new ones are ingested. A first group of approaches tackles forgetting by increasing deep model capacity to accommodate new knowledge. A second type of approaches fix the deep model size and introduce a mechanism whose objective is to ensure a good compromise between stability and plasticity of the model. While the first type of algorithms were compared thoroughly, this is not the case for methods which exploit a fixed size model. Here, we focus on the latter, place them in a common conceptual and experimental framework and propose the following contributions: (1) define six desirable properties of incremental learning algorithms and analyze them according to these properties, (2) introduce a unified formalization of the class-incremental learning problem, (3) propose a common evaluation framework which is more thorough than existing ones in terms of number of datasets, size of datasets, size of bounded memory and number of incremental states, (4) investigate the usefulness of herding for past exemplars selection, (5) provide experimental evidence that it is possible to obtain competitive performance without the use of knowledge distillation to tackle catastrophic forgetting and (6) facilitate reproducibility by integrating all tested methods in a common open-source repository. The main experimental finding is that none of the existing algorithms achieves the best results in all evaluated settings. Important differences arise notably if a bounded memory of past classes is allowed or not.
Code (1)
Tasks
class-incremental learningClass Incremental LearningIncremental LearningKnowledge DistillationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Comparative Study of Calibration Methods for Imbalanced Class Incremental Learning
Deep learning approaches are successful in a wide range of AI problems and in particular for visual recognition tasks. However, there are still open problems among which is the capacity to handle streams of visual inform…
class-incremental learningClass Incremental LearningIncremental LearningManagementUnsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns
Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera n…
Incremental LearningLearning-To-RankPerson Re-IdentificationTransfer Learning+1Recommendation of data-free class-incremental learning algorithms by simulating future data
Class-incremental learning deals with sequential data streams composed of batches of classes. Various algorithms have been proposed to address the challenging case where samples from past classes cannot be stored. Howeve…
class-incremental learningClass Incremental LearningIncremental LearningAudio-Visual Class-Incremental Learning
In this paper, we introduce audio-visual class-incremental learning, a class-incremental learning scenario for audio-visual video recognition. We demonstrate that joint audio-visual modeling can improve class-incremental…
class-incremental learningClass Incremental LearningIncremental LearningSemantic Similarity+2Evaluating the Efficacy of Instance Incremental vs. Batch Learning in Delayed Label Environments: An Empirical Study on Tabular Data Streaming for Fraud Detection
Real-world tabular learning production scenarios typically involve evolving data streams, where data arrives continuously and its distribution may change over time. In such a setting, most studies in the literature regar…
Computational EfficiencyFraud DetectionIncremental Learning