Adversarial Incremental Learning

2020-01-30 · Ankur Singh

Although deep learning performs really well in a wide variety of tasks, it still suffers from catastrophic forgetting -- the tendency of neural networks to forget previously learned information upon learning new tasks where previous data is not available. Earlier methods of incremental learning tackle this problem by either using a part of the old dataset, by generating exemplars or by using memory networks. Although, these methods have shown good results but using exemplars or generating them, increases memory and computation requirements. To solve these problems we propose an adversarial discriminator based method that does not make use of old data at all while training on new tasks. We particularly tackle the class incremental learning problem in image classification, where data is provided in a class-based sequential manner. For this problem, the network is trained using an adversarial loss along with the traditional cross-entropy loss. The cross-entropy loss helps the network progressively learn new classes while the adversarial loss helps in preserving information about the existing classes. Using this approach, we are able to outperform other state-of-the-art methods on CIFAR-100, SVHN, and MNIST datasets.

📄 PDF Abstract BibTeX arXiv:2001.11152

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learning Class Incremental Learning image-classification Image Classification Incremental Learning

Enhancing Robustness in Incremental Learning with Adversarial Training

2023-12-06 · Seungju Cho, Hongsin Lee, Changick Kim

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 Robustness class-incremental learning Class Incremental Learning Incremental Learning+1

Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation

2022-08-10 · Findings (NAACL) 2022 7 · Zhijing Wu, Hua Xu, Jingliang Fang, Kai Gao

Continual Machine Reading Comprehension aims to incrementally learn from a continuous data stream across time without access the previous seen data, which is crucial for the development of real-world MRC systems. However…

Domain Adaptation Incremental Learning Machine Reading Comprehension Reading Comprehension

Incremental Adversarial Domain Adaptation for Continually Changing Environments

2017-12-20 · Markus Wulfmeier, Alex Bewley, Ingmar Posner

Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current…

Domain Adaptation Generative Adversarial Network Unsupervised Domain Adaptation

Cross-Class Feature Augmentation for Class Incremental Learning

2023-04-04 · TaeHoon Kim, Jaeyoo Park, Bohyung Han

We propose a novel class incremental learning approach by incorporating a feature augmentation technique motivated by adversarial attacks. We employ a classifier learned in the past to complement training examples rather…

class-incremental learning Class Incremental Learning Incremental Learning Knowledge Distillation

FRIDA -- Generative Feature Replay for Incremental Domain Adaptation

2021-12-28 · Sayan Rakshit, Anwesh Mohanty, Ruchika Chavhan, Biplab Banerjee 외

We tackle the novel problem of incremental unsupervised domain adaptation (IDA) in this paper. We assume that a labeled source domain and different unlabeled target domains are incrementally observed with the constraint …