On Episodes, Prototypical Networks, and Few-Shot Learning
Dec 6, 2021
Speakers
Steinar Laenen
Speaker · 0 followers
Luca Bertinetto
Speaker · 0 followers
About
Episodic learning is a popular practice among researchers and practitioners interested in few-shot learning.It consists of organising training in a series of learning problems (or episodes), each divided into a small training and validation subset to mimic the circumstances encountered during evaluation. But is this always necessary?In this paper, we investigate the usefulness of episodic learning in methods which use nonparametric approaches, such as nearest neighbours, at the level of the episode. For these methods, we not only show how the constraints imposed by episodic learning are not necessary, but that they in fact lead to a data-inefficient way of exploiting training batches.We conduct a wide range of ablative experiments with Matching and Prototypical Networks, two of the most popular methods that use nonparametric approaches at the level of the episode. Their "non-episodic" counterparts are considerably simpler, and significantly improve their performance in multiple few-shot classification datasets.Episodic learning is a popular practice among researchers and practitioners interested in few-shot learning.It consists of organising training in a series of learning problems (or episodes), each divided into a small training and validation subset to mimic the circumstances encountered during evaluation. But is this always necessary?In this paper, we investigate the usefulness of episodic learning in methods which use nonparametric approaches, such as nearest neighbours, at the level of the epis…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Hierarchical Clustering: $O(1)$-Approximation for Well-Clustered Graphs
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Your Model is Wrong: Robustness and misspecification in probabilistic modeling
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Class-Incremental Learning via Dual Augmentation
Watch later
Fei Zhu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Invariance Principle Meets Information Bottleneck for OOD generalization
Watch later
Kartik Ahuja, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Science and Engineering of Intelligence
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%