0%

Learning to learn

INTRODUCTION

Learning to learn (i.e. meta learning, few-shot learning) is a set of learning methods, which tries to exploit the previous experience on other tasks to facilitate the learning process on the current task. Some interesting paper about few-shot learning/meta-learning are posted below.

OBJECT DETECTION

Kang, Bingyi, et al. “Few-shot object detection via feature reweighting.” Proceedings of the IEEE International Conference on Computer Vision. 2019.

SEGMENTATION

Caelles, Sergi, et al. “One-shot video object segmentation.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.

Shaban, Amirreza, et al. “One-shot learning for semantic segmentation.” arXiv preprint arXiv:1709.03410 (2017).

Wang, Kaixin, et al. “Panet: Few-shot image semantic segmentation with prototype alignment.” Proceedings of the IEEE International Conference on Computer Vision. 2019.

Zhang, Xiaolin, et al. “Sg-one: Similarity guidance network for one-shot semantic segmentation.” arXiv preprint arXiv:1810.09091 (2018).

LOW-LEVEL COMPUTER VISION

Casas, Leslie, et al. “Few-Shot Meta-Denoising.” arXiv preprint arXiv:1908.00111 (2019).

OPTIMIZATION

Vinyals, Oriol, et al. “Matching networks for one shot learning.” Advances in neural information processing systems. 2016.

Finn, Chelsea, Pieter Abbeel, and Sergey Levine. “Model-agnostic meta-learning for fast adaptation of deep networks.” Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 2017.

Nichol, Alex, Joshua Achiam, and John Schulman. “On first-order meta-learning algorithms.” arXiv preprint arXiv:1803.02999 (2018).

Snell, Jake, Kevin Swersky, and Richard Zemel. “Prototypical networks for few-shot learning.” Advances in neural information processing systems. 2017.

Ravi, Sachin, and Hugo Larochelle. “Optimization as a model for few-shot learning.” (2016).

Munkhdalai, Tsendsuren, and Hong Yu. “Meta networks.“ Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 2017.

Santoro, Adam, et al. “Meta-learning with memory-augmented neural networks.“ International conference on machine learning. 2016.