Class-incremental Learning via Deep Model Consolidation
| Autor: | Dawei Li, C.-C. Jay Kuo, Jie Zhang, Shalini Ghosh, Larry Heck, Serafettin Tasci, Heming Zhang, Junting Zhang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Training set Forgetting Contextual image classification Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Pascal (programming language) 010501 environmental sciences 01 natural sciences Object detection Machine Learning (cs.LG) Incremental learning 0202 electrical engineering electronic engineering information engineering Deep neural networks 020201 artificial intelligence & image processing Artificial intelligence Unavailability business computer 0105 earth and related environmental sciences computer.programming_language |
| Zdroj: | WACV |
| Popis: | Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of classes. Existing IL approaches tend to produce a model that is biased towards either the old classes or new classes, unless with the help of exemplars of the old data. To address this issue, we propose a class-incremental learning paradigm called Deep Model Consolidation (DMC), which works well even when the original training data is not available. The idea is to first train a separate model only for the new classes, and then combine the two individual models trained on data of two distinct set of classes (old classes and new classes) via a novel double distillation training objective. The two existing models are consolidated by exploiting publicly available unlabeled auxiliary data. This overcomes the potential difficulties due to the unavailability of original training data. Compared to the state-of-the-art techniques, DMC demonstrates significantly better performance in image classification (CIFAR-100 and CUB-200) and object detection (PASCAL VOC 2007) in the single-headed IL setting. WACV 2020 camera-ready |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|