paper-with-me

홈 › Papers

Improving Few-Shot Learning with Auxiliary Self-Supervised Pretext Tasks

2021-01-24 · Nathaniel Simard, Guillaume Lagrange

Recent work on few-shot learning \cite{tian2020rethinking} showed that quality of learned representations plays an important role in few-shot classification performance. On the other hand, the goal of self-supervised learning is to recover useful semantic information of the data without the use of class labels. In this work, we exploit the complementarity of both paradigms via a multi-task framework where we leverage recent self-supervised methods as auxiliary tasks. We found that combining multiple tasks is often beneficial, and that solving them simultaneously can be done efficiently. Our results suggest that self-supervised auxiliary tasks are effective data-dependent regularizers for representation learning. Our code is available at: \url{https://github.com/nathanielsimard/improving-fs-ssl}.

📄 PDF Abstract BibTeX arXiv:2101.09825

Code (1)

nathanielsimard/improving-fs-ssl 공식 구현 pytorch

Tasks

Few-Shot LearningRepresentation LearningSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Tailoring Self-Supervision for Supervised Learning

2022-07-20 · WonJun Moon, Ji-Hwan Kim, Jae-Pil Heo

Recently, it is shown that deploying a proper self-supervision is a prospective way to enhance the performance of supervised learning. Yet, the benefits of self-supervision are not fully exploited as previous pretext tas…

Adversarial RobustnessData AugmentationImage Classificationimbalanced classification+2

Multi-Pretext Attention Network for Few-shot Learning with Self-supervision

2021-03-10 · Hainan Li, Renshuai Tao, Jun Li, Haotong Qin 외

Few-shot learning is an interesting and challenging study, which enables machines to learn from few samples like humans. Existing studies rarely exploit auxiliary information from large amount of unlabeled data. Self-sup…

ClusteringFew-Shot LearningSelf-Supervised Learning

Investigating Self-Supervised Methods for Label-Efficient Learning

2024-06-25 · Srinivasa Rao Nandam, Sara Atito, ZhenHua Feng, Josef Kittler 외

Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification, segmentation and detection. The low-sh…

ClassificationClusteringContrastive LearningMulti-class Classification+5

Predicting What You Already Know Helps: Provable Self-Supervised Learning

2020-08-03 · NeurIPS 2021 12 · Jason D. Lee, Qi Lei, Nikunj Saunshi, Jiacheng Zhuo

Self-supervised representation learning solves auxiliary prediction tasks (known as pretext tasks) without requiring labeled data to learn useful semantic representations. These pretext tasks are created solely using the…

Representation LearningSelf-Supervised Learning

Improving out-of-distribution generalization via multi-task self-supervised pretraining

2020-03-30 · Isabela Albuquerque, Nikhil Naik, Junnan Li, Nitish Keskar 외

Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness. We show that features obtained using self-supervised learning are compara…

Adversarial RobustnessDomain GeneralizationFew-Shot LearningMulti-Task Learning+2