paper-with-me

홈 › Papers

Transfer Incremental Learning using Data Augmentation

2018-10-04 · Ghouthi Boukli Hacene, Vincent Gripon, Nicolas Farrugia, Matthieu Arzel, Michel Jezequel

Deep learning-based methods have reached state of the art performances, relying on large quantity of available data and computational power. Such methods still remain highly inappropriate when facing a major open machine learning problem, which consists of learning incrementally new classes and examples over time. Combining the outstanding performances of Deep Neural Networks (DNNs) with the flexibility of incremental learning techniques is a promising venue of research. In this contribution, we introduce Transfer Incremental Learning using Data Augmentation (TILDA). TILDA is based on pre-trained DNNs as feature extractor, robust selection of feature vectors in subspaces using a nearest-class-mean based technique, majority votes and data augmentation at both the training and the prediction stages. Experiments on challenging vision datasets demonstrate the ability of the proposed method for low complexity incremental learning, while achieving significantly better accuracy than existing incremental counterparts.

📄 PDF Abstract BibTeX arXiv:1810.02020

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationIncremental Learning

Similar Papers 제목 키워드 기반

Class-Incremental Learning via Dual Augmentation

2021-12-01 · NeurIPS 2021 12 · Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu

Deep learning systems typically suffer from catastrophic forgetting of past knowledge when acquiring new skills continually. In this paper, we emphasize two dilemmas, representation bias and classifier bias in class-incr…

class-incremental learningClass Incremental LearningIncremental Learning

Enhancing Visual Perception in Novel Environments via Incremental Data Augmentation Based on Style Transfer

2023-09-16 · Abhibha Gupta, Rully Agus Hendrawan, Mansur Arief

The deployment of autonomous agents in real-world scenarios is challenged by "unknown unknowns", i.e. novel unexpected environments not encountered during training, such as degraded signs. While existing research focuses…

Anomaly DetectionData AugmentationStyle Transfer

Knowledge Transfer-Driven Few-Shot Class-Incremental Learning

2023-06-19 · Ye Wang, Yaxiong Wang, Guoshuai Zhao, Xueming Qian

Few-shot class-incremental learning (FSCIL) aims to continually learn new classes using a few samples while not forgetting the old classes. The key of this task is effective knowledge transfer from the base session to th…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning+1

Prototype Augmentation and Self-Supervision for Incremental Learning

2021-06-19 · CVPR 2021 1 · Fei Zhu, Xu-Yao Zhang, Chuang Wang, Fei Yin 외

Despite the impressive performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning new tasks incrementally. Recently, various incremental learning methods have been pr…

Incremental LearningSelf-Supervised Learning

On Robust Incremental Learning over Many Multilingual Steps

2022-10-25 · Karan Praharaj, Irina Matveeva

Recent work in incremental learning has introduced diverse approaches to tackle catastrophic forgetting from data augmentation to optimized training regimes. However, most of them focus on very few training steps. We pro…

Data AugmentationIncremental Learning