Continual Learning with Evolving Class Ontologies
Lifelong learners must recognize concept vocabularies that evolve over time. A common yet underexplored scenario is learning with class labels that continually refine/expand old classes. For example, humans learn to recognize ${\tt dog}$ before dog breeds. In practical settings, dataset $\textit{versioning}$ often introduces refinement to ontologies, such as autonomous vehicle benchmarks that refine a previous ${\tt vehicle}$ class into ${\tt school-bus}$ as autonomous operations expand to new cities. This paper formalizes a protocol for studying the problem of $\textit{Learning with Evolving Class Ontology}$ (LECO). LECO requires learning classifiers in distinct time periods (TPs); each TP introduces a new ontology of "fine" labels that refines old ontologies of "coarse" labels (e.g., dog breeds that refine the previous ${\tt dog}$). LECO explores such questions as whether to annotate new data or relabel the old, how to leverage coarse labels, and whether to finetune the previous TP's model or train from scratch. To answer these questions, we leverage insights from related problems such as class-incremental learning. We validate them under the LECO protocol through the lens of image classification (CIFAR and iNaturalist) and semantic segmentation (Mapillary). Our experiments lead to surprising conclusions; while the current status quo is to relabel existing datasets with new ontologies (such as COCO-to-LVIS or Mapillary1.2-to-2.0), LECO demonstrates that a far better strategy is to annotate $\textit{new}$ data with the new ontology. However, this produces an aggregate dataset with inconsistent old-vs-new labels, complicating learning. To address this challenge, we adopt methods from semi-supervised and partial-label learning. Such strategies can surprisingly be made near-optimal, approaching an "oracle" that learns on the aggregate dataset exhaustively labeled with the newest ontology.
Code (0)
등록된 구현이 없습니다.
Tasks
class-incremental learningClass Incremental LearningContinual Learningimage-classificationImage ClassificationIncremental LearningPartial Label LearningSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CLEO: Continual Learning of Evolving Ontologies
Continual learning (CL) addresses the problem of catastrophic forgetting in neural networks, which occurs when a trained model tends to overwrite previously learned information, when presented with a new task. CL aims to…
Autonomous DrivingContinual LearningIncremental LearningLifelong learningContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations
Toxicity detection mitigates the dissemination of toxic content (e.g., hateful comments, posts, and messages within online social actions) to safeguard a healthy online social environment. However, malicious users persis…
Continual LearningPrimeKG-CL: A Continual Graph Learning Benchmark on Evolving Biomedical Knowledge Graphs
Biomedical knowledge graphs underwrite drug repurposing and clinical decision support, yet the upstream ontologies they depend on update on independent cycles that add millions of edges and deprecate hundreds of thousand…
Continual LearningKnowledge GraphsGraph LearningInstance-Aware Test-Time Segmentation for Continual Domain Shifts
Continual Test-Time Adaptation (CTTA) enables pre-trained models to adapt to continuously evolving domains. Existing methods have improved robustness but typically rely on fixed or batch-level thresholds, which cannot ac…
Semantic SegmentationTest-time AdaptationIn-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory
Continually learning new classes from a few training examples without forgetting previous old classes demands a flexible architecture with an inevitably growing portion of storage, in which new examples and classes can b…
Continual Learning