Incremental Learning Using Conditional Adversarial Networks
Incremental learning using Deep Neural Networks (DNNs) suffers from catastrophic forgetting. Existing methods mitigate it by either storing old image examples or only updating a few fully connected layers of DNNs, which, however, requires large memory footprints or hurts the plasticity of models. In this paper, we propose a new incremental learning strategy based on conditional adversarial networks. Our new strategy allows us to use memory-efficient statistical information to store old knowledge, and fine-tune both convolutional layers and fully connected layers to consolidate new knowledge. Specifically, we propose a model consisting of three parts, i.e., a base sub-net, a generator, and a discriminator. The base sub-net works as a feature extractor which can be pre-trained on large scale datasets and shared across multiple image recognition tasks. The generator conditioned on labeled embeddings aims to construct pseudo-examples with the same distribution as the old data. The discriminator combines real-examples from new data and pseudo-examples generated from the old data distribution to learn representation for both old and new classes. Through adversarial training of the discriminator and generator, we accomplish the multiple continuous incremental learning. Comparison with the state-of-the-arts on public CIFAR-100 and CUB-200 datasets shows that our method achieves the best accuracies on both old and new classes while requiring relatively less memory storage.
Code (0)
등록된 구현이 없습니다.
Tasks
Incremental LearningSimilar Papers 제목 키워드 기반
Incremental Concept Learning via Online Generative Memory Recall
The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previousl…
class-incremental learningClass Incremental LearningGenerative Adversarial NetworkIncremental LearningPainting on Placement: Forecasting Routing Congestion using Conditional Generative Adversarial Nets
Physical design process commonly consumes hours to days for large designs, and routing is known as the most critical step. Demands for accurate routing quality prediction raise to a new level to accelerate hardware innov…
ColorizationTranslationORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning
Continual learning usually assumes the incoming data are fully labeled, which might not be applicable in real applications. In this work, we consider semi-supervised continual learning (SSCL) that incrementally learns fr…
Continual LearningGenerative Adversarial NetworkEnhancing Robustness in Incremental Learning with Adversarial Training
Adversarial training is one of the most effective approaches against adversarial attacks. However, adversarial training has primarily been studied in scenarios where data for all classes is provided, with limited researc…
Adversarial Robustnessclass-incremental learningClass Incremental LearningIncremental Learning+1Learning to remember: Dynamic Generative Memory for Continual Learning
Continuously trainable models should be able to learn from a stream of data over an undefined period of time. This becomes even more difficult in a strictly incremental context, where data access to previously seen categ…
Continual Learning